From 36d22d82aa202bb199967e9512281e9a53db42c9 Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Sun, 7 Apr 2024 21:33:14 +0200 Subject: Adding upstream version 115.7.0esr. Signed-off-by: Daniel Baumann --- third_party/python/PyYAML/CHANGES | 254 ++++ third_party/python/PyYAML/LICENSE | 20 + third_party/python/PyYAML/MANIFEST.in | 10 + third_party/python/PyYAML/Makefile | 44 + third_party/python/PyYAML/PKG-INFO | 44 + third_party/python/PyYAML/README | 43 + .../PyYAML/examples/pygments-lexer/example.yaml | 302 ++++ .../python/PyYAML/examples/pygments-lexer/yaml.py | 431 ++++++ .../PyYAML/examples/yaml-highlight/yaml_hl.cfg | 115 ++ .../PyYAML/examples/yaml-highlight/yaml_hl.py | 114 ++ third_party/python/PyYAML/lib/_yaml/__init__.py | 33 + third_party/python/PyYAML/lib/yaml/__init__.py | 431 ++++++ third_party/python/PyYAML/lib/yaml/composer.py | 139 ++ third_party/python/PyYAML/lib/yaml/constructor.py | 766 ++++++++++ third_party/python/PyYAML/lib/yaml/cyaml.py | 101 ++ third_party/python/PyYAML/lib/yaml/dumper.py | 62 + third_party/python/PyYAML/lib/yaml/emitter.py | 1144 +++++++++++++++ third_party/python/PyYAML/lib/yaml/error.py | 75 + third_party/python/PyYAML/lib/yaml/events.py | 86 ++ third_party/python/PyYAML/lib/yaml/loader.py | 63 + third_party/python/PyYAML/lib/yaml/nodes.py | 49 + third_party/python/PyYAML/lib/yaml/parser.py | 589 ++++++++ third_party/python/PyYAML/lib/yaml/reader.py | 193 +++ third_party/python/PyYAML/lib/yaml/representer.py | 489 +++++++ third_party/python/PyYAML/lib/yaml/resolver.py | 227 +++ third_party/python/PyYAML/lib/yaml/scanner.py | 1444 ++++++++++++++++++ third_party/python/PyYAML/lib/yaml/serializer.py | 111 ++ third_party/python/PyYAML/lib/yaml/tokens.py | 104 ++ .../python/PyYAML/lib3/PyYAML.egg-info/PKG-INFO | 44 + .../python/PyYAML/lib3/PyYAML.egg-info/SOURCES.txt | 670 +++++++++ .../lib3/PyYAML.egg-info/dependency_links.txt | 1 + .../PyYAML/lib3/PyYAML.egg-info/top_level.txt | 2 + third_party/python/PyYAML/lib3/_yaml/__init__.py | 33 + third_party/python/PyYAML/lib3/yaml/__init__.py | 427 ++++++ third_party/python/PyYAML/lib3/yaml/composer.py | 139 ++ third_party/python/PyYAML/lib3/yaml/constructor.py | 748 ++++++++++ third_party/python/PyYAML/lib3/yaml/cyaml.py | 101 ++ third_party/python/PyYAML/lib3/yaml/dumper.py | 62 + third_party/python/PyYAML/lib3/yaml/emitter.py | 1137 +++++++++++++++ third_party/python/PyYAML/lib3/yaml/error.py | 75 + third_party/python/PyYAML/lib3/yaml/events.py | 86 ++ third_party/python/PyYAML/lib3/yaml/loader.py | 63 + third_party/python/PyYAML/lib3/yaml/nodes.py | 49 + third_party/python/PyYAML/lib3/yaml/parser.py | 589 ++++++++ third_party/python/PyYAML/lib3/yaml/reader.py | 185 +++ third_party/python/PyYAML/lib3/yaml/representer.py | 389 +++++ third_party/python/PyYAML/lib3/yaml/resolver.py | 227 +++ third_party/python/PyYAML/lib3/yaml/scanner.py | 1435 ++++++++++++++++++ third_party/python/PyYAML/lib3/yaml/serializer.py | 111 ++ third_party/python/PyYAML/lib3/yaml/tokens.py | 104 ++ third_party/python/PyYAML/pyproject.toml | 3 + third_party/python/PyYAML/setup.cfg | 9 + third_party/python/PyYAML/setup.py | 296 ++++ third_party/python/PyYAML/yaml/__init__.pxd | 0 third_party/python/PyYAML/yaml/_yaml.h | 23 + third_party/python/PyYAML/yaml/_yaml.pxd | 251 ++++ third_party/python/PyYAML/yaml/_yaml.pyx | 1527 ++++++++++++++++++++ 57 files changed, 16269 insertions(+) create mode 100644 third_party/python/PyYAML/CHANGES create mode 100644 third_party/python/PyYAML/LICENSE create mode 100644 third_party/python/PyYAML/MANIFEST.in create mode 100644 third_party/python/PyYAML/Makefile create mode 100644 third_party/python/PyYAML/PKG-INFO create mode 100644 third_party/python/PyYAML/README create mode 100644 third_party/python/PyYAML/examples/pygments-lexer/example.yaml create mode 100644 third_party/python/PyYAML/examples/pygments-lexer/yaml.py create mode 100644 third_party/python/PyYAML/examples/yaml-highlight/yaml_hl.cfg create mode 100755 third_party/python/PyYAML/examples/yaml-highlight/yaml_hl.py create mode 100644 third_party/python/PyYAML/lib/_yaml/__init__.py create mode 100644 third_party/python/PyYAML/lib/yaml/__init__.py create mode 100644 third_party/python/PyYAML/lib/yaml/composer.py create mode 100644 third_party/python/PyYAML/lib/yaml/constructor.py create mode 100644 third_party/python/PyYAML/lib/yaml/cyaml.py create mode 100644 third_party/python/PyYAML/lib/yaml/dumper.py create mode 100644 third_party/python/PyYAML/lib/yaml/emitter.py create mode 100644 third_party/python/PyYAML/lib/yaml/error.py create mode 100644 third_party/python/PyYAML/lib/yaml/events.py create mode 100644 third_party/python/PyYAML/lib/yaml/loader.py create mode 100644 third_party/python/PyYAML/lib/yaml/nodes.py create mode 100644 third_party/python/PyYAML/lib/yaml/parser.py create mode 100644 third_party/python/PyYAML/lib/yaml/reader.py create mode 100644 third_party/python/PyYAML/lib/yaml/representer.py create mode 100644 third_party/python/PyYAML/lib/yaml/resolver.py create mode 100644 third_party/python/PyYAML/lib/yaml/scanner.py create mode 100644 third_party/python/PyYAML/lib/yaml/serializer.py create mode 100644 third_party/python/PyYAML/lib/yaml/tokens.py create mode 100644 third_party/python/PyYAML/lib3/PyYAML.egg-info/PKG-INFO create mode 100644 third_party/python/PyYAML/lib3/PyYAML.egg-info/SOURCES.txt create mode 100644 third_party/python/PyYAML/lib3/PyYAML.egg-info/dependency_links.txt create mode 100644 third_party/python/PyYAML/lib3/PyYAML.egg-info/top_level.txt create mode 100644 third_party/python/PyYAML/lib3/_yaml/__init__.py create mode 100644 third_party/python/PyYAML/lib3/yaml/__init__.py create mode 100644 third_party/python/PyYAML/lib3/yaml/composer.py create mode 100644 third_party/python/PyYAML/lib3/yaml/constructor.py create mode 100644 third_party/python/PyYAML/lib3/yaml/cyaml.py create mode 100644 third_party/python/PyYAML/lib3/yaml/dumper.py create mode 100644 third_party/python/PyYAML/lib3/yaml/emitter.py create mode 100644 third_party/python/PyYAML/lib3/yaml/error.py create mode 100644 third_party/python/PyYAML/lib3/yaml/events.py create mode 100644 third_party/python/PyYAML/lib3/yaml/loader.py create mode 100644 third_party/python/PyYAML/lib3/yaml/nodes.py create mode 100644 third_party/python/PyYAML/lib3/yaml/parser.py create mode 100644 third_party/python/PyYAML/lib3/yaml/reader.py create mode 100644 third_party/python/PyYAML/lib3/yaml/representer.py create mode 100644 third_party/python/PyYAML/lib3/yaml/resolver.py create mode 100644 third_party/python/PyYAML/lib3/yaml/scanner.py create mode 100644 third_party/python/PyYAML/lib3/yaml/serializer.py create mode 100644 third_party/python/PyYAML/lib3/yaml/tokens.py create mode 100644 third_party/python/PyYAML/pyproject.toml create mode 100644 third_party/python/PyYAML/setup.cfg create mode 100644 third_party/python/PyYAML/setup.py create mode 100644 third_party/python/PyYAML/yaml/__init__.pxd create mode 100644 third_party/python/PyYAML/yaml/_yaml.h create mode 100644 third_party/python/PyYAML/yaml/_yaml.pxd create mode 100644 third_party/python/PyYAML/yaml/_yaml.pyx (limited to 'third_party/python/PyYAML') diff --git a/third_party/python/PyYAML/CHANGES b/third_party/python/PyYAML/CHANGES new file mode 100644 index 0000000000..8d647a597c --- /dev/null +++ b/third_party/python/PyYAML/CHANGES @@ -0,0 +1,254 @@ + +For a complete changelog, see: + +* https://github.com/yaml/pyyaml/commits/ +* https://bitbucket.org/xi/pyyaml/commits/ + +5.4.1 (2021-01-20) + +* https://github.com/yaml/pyyaml/pull/480 -- Fix stub compat with older pyyaml versions that may unwittingly load it + +5.4 (2021-01-19) + +* https://github.com/yaml/pyyaml/pull/407 -- Build modernization, remove distutils, fix metadata, build wheels, CI to GHA +* https://github.com/yaml/pyyaml/pull/472 -- Fix for CVE-2020-14343, moves arbitrary python tags to UnsafeLoader +* https://github.com/yaml/pyyaml/pull/441 -- Fix memory leak in implicit resolver setup +* https://github.com/yaml/pyyaml/pull/392 -- Fix py2 copy support for timezone objects +* https://github.com/yaml/pyyaml/pull/378 -- Fix compatibility with Jython + +5.3.1 (2020-03-18) + +* https://github.com/yaml/pyyaml/pull/386 -- Prevents arbitrary code execution during python/object/new constructor + +5.3 (2020-01-06) + +* https://github.com/yaml/pyyaml/pull/290 -- Use `is` instead of equality for comparing with `None` +* https://github.com/yaml/pyyaml/pull/270 -- Fix typos and stylistic nit +* https://github.com/yaml/pyyaml/pull/309 -- Fix up small typo +* https://github.com/yaml/pyyaml/pull/161 -- Fix handling of __slots__ +* https://github.com/yaml/pyyaml/pull/358 -- Allow calling add_multi_constructor with None +* https://github.com/yaml/pyyaml/pull/285 -- Add use of safe_load() function in README +* https://github.com/yaml/pyyaml/pull/351 -- Fix reader for Unicode code points over 0xFFFF +* https://github.com/yaml/pyyaml/pull/360 -- Enable certain unicode tests when maxunicode not > 0xffff +* https://github.com/yaml/pyyaml/pull/359 -- Use full_load in yaml-highlight example +* https://github.com/yaml/pyyaml/pull/244 -- Document that PyYAML is implemented with Cython +* https://github.com/yaml/pyyaml/pull/329 -- Fix for Python 3.10 +* https://github.com/yaml/pyyaml/pull/310 -- Increase size of index, line, and column fields +* https://github.com/yaml/pyyaml/pull/260 -- Remove some unused imports +* https://github.com/yaml/pyyaml/pull/163 -- Create timezone-aware datetimes when parsed as such +* https://github.com/yaml/pyyaml/pull/363 -- Add tests for timezone + +5.2 (2019-12-02) +------------------ + +* Repair incompatibilities introduced with 5.1. The default Loader was changed, + but several methods like add_constructor still used the old default + https://github.com/yaml/pyyaml/pull/279 -- A more flexible fix for custom tag constructors + https://github.com/yaml/pyyaml/pull/287 -- Change default loader for yaml.add_constructor + https://github.com/yaml/pyyaml/pull/305 -- Change default loader for add_implicit_resolver, add_path_resolver +* Make FullLoader safer by removing python/object/apply from the default FullLoader + https://github.com/yaml/pyyaml/pull/347 -- Move constructor for object/apply to UnsafeConstructor +* Fix bug introduced in 5.1 where quoting went wrong on systems with sys.maxunicode <= 0xffff + https://github.com/yaml/pyyaml/pull/276 -- Fix logic for quoting special characters +* Other PRs: + https://github.com/yaml/pyyaml/pull/280 -- Update CHANGES for 5.1 + +5.1.2 (2019-07-30) +------------------ + +* Re-release of 5.1 with regenerated Cython sources to build properly for Python 3.8b2+ + +5.1.1 (2019-06-05) +------------------ + +* Re-release of 5.1 with regenerated Cython sources to build properly for Python 3.8b1 + +5.1 (2019-03-13) +---------------- + +* https://github.com/yaml/pyyaml/pull/35 -- Some modernization of the test running +* https://github.com/yaml/pyyaml/pull/42 -- Install tox in a virtualenv +* https://github.com/yaml/pyyaml/pull/45 -- Allow colon in a plain scalar in a flow context +* https://github.com/yaml/pyyaml/pull/48 -- Fix typos +* https://github.com/yaml/pyyaml/pull/55 -- Improve RepresenterError creation +* https://github.com/yaml/pyyaml/pull/59 -- Resolves #57, update readme issues link +* https://github.com/yaml/pyyaml/pull/60 -- Document and test Python 3.6 support +* https://github.com/yaml/pyyaml/pull/61 -- Use Travis CI built in pip cache support +* https://github.com/yaml/pyyaml/pull/62 -- Remove tox workaround for Travis CI +* https://github.com/yaml/pyyaml/pull/63 -- Adding support to Unicode characters over codepoint 0xffff +* https://github.com/yaml/pyyaml/pull/75 -- add 3.12 changelog +* https://github.com/yaml/pyyaml/pull/76 -- Fallback to Pure Python if Compilation fails +* https://github.com/yaml/pyyaml/pull/84 -- Drop unsupported Python 3.3 +* https://github.com/yaml/pyyaml/pull/102 -- Include license file in the generated wheel package +* https://github.com/yaml/pyyaml/pull/105 -- Removed Python 2.6 & 3.3 support +* https://github.com/yaml/pyyaml/pull/111 -- Remove commented out Psyco code +* https://github.com/yaml/pyyaml/pull/129 -- Remove call to `ord` in lib3 emitter code +* https://github.com/yaml/pyyaml/pull/149 -- Test on Python 3.7-dev +* https://github.com/yaml/pyyaml/pull/158 -- Support escaped slash in double quotes "\/" +* https://github.com/yaml/pyyaml/pull/175 -- Updated link to pypi in release announcement +* https://github.com/yaml/pyyaml/pull/181 -- Import Hashable from collections.abc +* https://github.com/yaml/pyyaml/pull/194 -- Reverting https://github.com/yaml/pyyaml/pull/74 +* https://github.com/yaml/pyyaml/pull/195 -- Build libyaml on travis +* https://github.com/yaml/pyyaml/pull/196 -- Force cython when building sdist +* https://github.com/yaml/pyyaml/pull/254 -- Allow to turn off sorting keys in Dumper (2) +* https://github.com/yaml/pyyaml/pull/256 -- Make default_flow_style=False +* https://github.com/yaml/pyyaml/pull/257 -- Deprecate yaml.load and add FullLoader and UnsafeLoader classes +* https://github.com/yaml/pyyaml/pull/261 -- Skip certain unicode tests when maxunicode not > 0xffff +* https://github.com/yaml/pyyaml/pull/263 -- Windows Appveyor build + +3.13 (2018-07-05) +----------------- + +* Resolved issues around PyYAML working in Python 3.7. + +3.12 (2016-08-28) +----------------- + +* Wheel packages for Windows binaries. +* Adding an implicit resolver to a derived loader should not affect the base loader. +* Uniform representation for OrderedDict? across different versions of Python. +* Fixed comparison to None warning. + +3.11 (2014-03-26) +----------------- + +* Source and binary distributions are rebuilt against the latest + versions of Cython and LibYAML. + +3.10 (2011-05-30) +----------------- + +* Do not try to build LibYAML bindings on platforms other than CPython + (Thank to olt(at)bogosoft(dot)com). +* Clear cyclic references in the parser and the emitter + (Thank to kristjan(at)ccpgames(dot)com). +* Dropped support for Python 2.3 and 2.4. + +3.09 (2009-08-31) +----------------- + +* Fixed an obscure scanner error not reported when there is + no line break at the end of the stream (Thank to Ingy). +* Fixed use of uninitialized memory when emitting anchors with + LibYAML bindings (Thank to cegner(at)yahoo-inc(dot)com). +* Fixed emitting incorrect BOM characters for UTF-16 (Thank to + Valentin Nechayev) +* Fixed the emitter for folded scalars not respecting the preferred + line width (Thank to Ingy). +* Fixed a subtle ordering issue with emitting '%TAG' directives + (Thank to Andrey Somov). +* Fixed performance regression with LibYAML bindings. + + +3.08 (2008-12-31) +----------------- + +* Python 3 support (Thank to Erick Tryzelaar). +* Use Cython instead of Pyrex to build LibYAML bindings. +* Refactored support for unicode and byte input/output streams. + + +3.07 (2008-12-29) +----------------- + +* The emitter learned to use an optional indentation indicator + for block scalar; thus scalars with leading whitespaces + could now be represented in a literal or folded style. +* The test suite is now included in the source distribution. + To run the tests, type 'python setup.py test'. +* Refactored the test suite: dropped unittest in favor of + a custom test appliance. +* Fixed the path resolver in CDumper. +* Forced an explicit document end indicator when there is + a possibility of parsing ambiguity. +* More setup.py improvements: the package should be usable + when any combination of setuptools, Pyrex and LibYAML + is installed. +* Windows binary packages are built against LibYAML-0.1.2. +* Minor typos and corrections (Thank to Ingy dot Net + and Andrey Somov). + + +3.06 (2008-10-03) +----------------- + +* setup.py checks whether LibYAML is installed and if so, builds + and installs LibYAML bindings. To force or disable installation + of LibYAML bindings, use '--with-libyaml' or '--without-libyaml' + respectively. +* The source distribution includes compiled Pyrex sources so + building LibYAML bindings no longer requires Pyrex installed. +* 'yaml.load()' raises an exception if the input stream contains + more than one YAML document. +* Fixed exceptions produced by LibYAML bindings. +* Fixed a dot '.' character being recognized as !!float. +* Fixed Python 2.3 compatibility issue in constructing !!timestamp values. +* Windows binary packages are built against the LibYAML stable branch. +* Added attributes 'yaml.__version__' and 'yaml.__with_libyaml__'. + + +3.05 (2007-05-13) +----------------- + +* Windows binary packages were built with LibYAML trunk. +* Fixed a bug that prevent processing a live stream of YAML documents in + timely manner (Thanks edward(at)sweetbytes(dot)net). +* Fixed a bug when the path in add_path_resolver contains boolean values + (Thanks jstroud(at)mbi(dot)ucla(dot)edu). +* Fixed loss of microsecond precision in timestamps + (Thanks edemaine(at)mit(dot)edu). +* Fixed loading an empty YAML stream. +* Allowed immutable subclasses of YAMLObject. +* Made the encoding of the unicode->str conversion explicit so that + the conversion does not depend on the default Python encoding. +* Forced emitting float values in a YAML compatible form. + + +3.04 (2006-08-20) +----------------- + +* Include experimental LibYAML bindings. +* Fully support recursive structures. +* Sort dictionary keys. Mapping node values are now represented + as lists of pairs instead of dictionaries. No longer check + for duplicate mapping keys as it didn't work correctly anyway. +* Fix invalid output of single-quoted scalars in cases when a single + quote is not escaped when preceded by whitespaces or line breaks. +* To make porting easier, rewrite Parser not using generators. +* Fix handling of unexpected block mapping values. +* Fix a bug in Representer.represent_object: copy_reg.dispatch_table + was not correctly handled. +* Fix a bug when a block scalar is incorrectly emitted in the simple + key context. +* Hold references to the objects being represented. +* Make Representer not try to guess !!pairs when a list is represented. +* Fix timestamp constructing and representing. +* Fix the 'N' plain scalar being incorrectly recognized as !!bool. + + +3.03 (2006-06-19) +----------------- + +* Fix Python 2.5 compatibility issues. +* Fix numerous bugs in the float handling. +* Fix scanning some ill-formed documents. +* Other minor fixes. + + +3.02 (2006-05-15) +----------------- + +* Fix win32 installer. Apparently bdist_wininst does not work well + under Linux. +* Fix a bug in add_path_resolver. +* Add the yaml-highlight example. Try to run on a color terminal: + `python yaml_hl.py =2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.* diff --git a/third_party/python/PyYAML/README b/third_party/python/PyYAML/README new file mode 100644 index 0000000000..49c87e7642 --- /dev/null +++ b/third_party/python/PyYAML/README @@ -0,0 +1,43 @@ +PyYAML - The next generation YAML parser and emitter for Python. + +To install, type 'python setup.py install'. + +By default, the setup.py script checks whether LibYAML is installed +and if so, builds and installs LibYAML bindings. To skip the check +and force installation of LibYAML bindings, use the option '--with-libyaml': +'python setup.py --with-libyaml install'. To disable the check and +skip building and installing LibYAML bindings, use '--without-libyaml': +'python setup.py --without-libyaml install'. + +When LibYAML bindings are installed, you may use fast LibYAML-based +parser and emitter as follows: + + >>> yaml.load(stream, Loader=yaml.CLoader) + >>> yaml.dump(data, Dumper=yaml.CDumper) + +If you don't trust the input stream, you should use: + + >>> yaml.safe_load(stream) + +PyYAML includes a comprehensive test suite. To run the tests, +type 'python setup.py test'. + +For more information, check the PyYAML homepage: +'https://github.com/yaml/pyyaml'. + +For PyYAML tutorial and reference, see: +'http://pyyaml.org/wiki/PyYAMLDocumentation'. + +Discuss PyYAML with the maintainers in IRC #pyyaml irc.freenode.net. + +You may also use the YAML-Core mailing list: +'http://lists.sourceforge.net/lists/listinfo/yaml-core'. + +Submit bug reports and feature requests to the PyYAML bug tracker: +'https://github.com/yaml/pyyaml/issues'. + +The PyYAML module was written by Kirill Simonov . +It is currently maintained by the YAML and Python communities. + +PyYAML is released under the MIT license. +See the file LICENSE for more details. diff --git a/third_party/python/PyYAML/examples/pygments-lexer/example.yaml b/third_party/python/PyYAML/examples/pygments-lexer/example.yaml new file mode 100644 index 0000000000..9c0ed9d082 --- /dev/null +++ b/third_party/python/PyYAML/examples/pygments-lexer/example.yaml @@ -0,0 +1,302 @@ + +# +# Examples from the Preview section of the YAML specification +# (http://yaml.org/spec/1.2/#Preview) +# + +# Sequence of scalars +--- +- Mark McGwire +- Sammy Sosa +- Ken Griffey + +# Mapping scalars to scalars +--- +hr: 65 # Home runs +avg: 0.278 # Batting average +rbi: 147 # Runs Batted In + +# Mapping scalars to sequences +--- +american: + - Boston Red Sox + - Detroit Tigers + - New York Yankees +national: + - New York Mets + - Chicago Cubs + - Atlanta Braves + +# Sequence of mappings +--- +- + name: Mark McGwire + hr: 65 + avg: 0.278 +- + name: Sammy Sosa + hr: 63 + avg: 0.288 + +# Sequence of sequences +--- +- [name , hr, avg ] +- [Mark McGwire, 65, 0.278] +- [Sammy Sosa , 63, 0.288] + +# Mapping of mappings +--- +Mark McGwire: {hr: 65, avg: 0.278} +Sammy Sosa: { + hr: 63, + avg: 0.288 + } + +# Two documents in a stream +--- # Ranking of 1998 home runs +- Mark McGwire +- Sammy Sosa +- Ken Griffey +--- # Team ranking +- Chicago Cubs +- St Louis Cardinals + +# Documents with the end indicator +--- +time: 20:03:20 +player: Sammy Sosa +action: strike (miss) +... +--- +time: 20:03:47 +player: Sammy Sosa +action: grand slam +... + +# Comments +--- +hr: # 1998 hr ranking + - Mark McGwire + - Sammy Sosa +rbi: + # 1998 rbi ranking + - Sammy Sosa + - Ken Griffey + +# Anchors and aliases +--- +hr: + - Mark McGwire + # Following node labeled SS + - &SS Sammy Sosa +rbi: + - *SS # Subsequent occurrence + - Ken Griffey + +# Mapping between sequences +--- +? - Detroit Tigers + - Chicago cubs +: + - 2001-07-23 +? [ New York Yankees, + Atlanta Braves ] +: [ 2001-07-02, 2001-08-12, + 2001-08-14 ] + +# Inline nested mapping +--- +# products purchased +- item : Super Hoop + quantity: 1 +- item : Basketball + quantity: 4 +- item : Big Shoes + quantity: 1 + +# Literal scalars +--- | # ASCII art + \//||\/|| + // || ||__ + +# Folded scalars +--- > + Mark McGwire's + year was crippled + by a knee injury. + +# Preserved indented block in a folded scalar +--- +> + Sammy Sosa completed another + fine season with great stats. + + 63 Home Runs + 0.288 Batting Average + + What a year! + +# Indentation determines scope +--- +name: Mark McGwire +accomplishment: > + Mark set a major league + home run record in 1998. +stats: | + 65 Home Runs + 0.278 Batting Average + +# Quoted scalars +--- +unicode: "Sosa did fine.\u263A" +control: "\b1998\t1999\t2000\n" +hex esc: "\x0d\x0a is \r\n" +single: '"Howdy!" he cried.' +quoted: ' # not a ''comment''.' +tie-fighter: '|\-*-/|' + +# Multi-line flow scalars +--- +plain: + This unquoted scalar + spans many lines. +quoted: "So does this + quoted scalar.\n" + +# Integers +--- +canonical: 12345 +decimal: +12_345 +sexagesimal: 3:25:45 +octal: 014 +hexadecimal: 0xC + +# Floating point +--- +canonical: 1.23015e+3 +exponential: 12.3015e+02 +sexagesimal: 20:30.15 +fixed: 1_230.15 +negative infinity: -.inf +not a number: .NaN + +# Miscellaneous +--- +null: ~ +true: boolean +false: boolean +string: '12345' + +# Timestamps +--- +canonical: 2001-12-15T02:59:43.1Z +iso8601: 2001-12-14t21:59:43.10-05:00 +spaced: 2001-12-14 21:59:43.10 -5 +date: 2002-12-14 + +# Various explicit tags +--- +not-date: !!str 2002-04-28 +picture: !!binary | + R0lGODlhDAAMAIQAAP//9/X + 17unp5WZmZgAAAOfn515eXv + Pz7Y6OjuDg4J+fn5OTk6enp + 56enmleECcgggoBADs= +application specific tag: !something | + The semantics of the tag + above may be different for + different documents. + +# Global tags +%TAG ! tag:clarkevans.com,2002: +--- !shape + # Use the ! handle for presenting + # tag:clarkevans.com,2002:circle +- !circle + center: &ORIGIN {x: 73, y: 129} + radius: 7 +- !line + start: *ORIGIN + finish: { x: 89, y: 102 } +- !label + start: *ORIGIN + color: 0xFFEEBB + text: Pretty vector drawing. + +# Unordered sets +--- !!set +# sets are represented as a +# mapping where each key is +# associated with the empty string +? Mark McGwire +? Sammy Sosa +? Ken Griff + +# Ordered mappings +--- !!omap +# ordered maps are represented as +# a sequence of mappings, with +# each mapping having one key +- Mark McGwire: 65 +- Sammy Sosa: 63 +- Ken Griffy: 58 + +# Full length example +--- ! +invoice: 34843 +date : 2001-01-23 +bill-to: &id001 + given : Chris + family : Dumars + address: + lines: | + 458 Walkman Dr. + Suite #292 + city : Royal Oak + state : MI + postal : 48046 +ship-to: *id001 +product: + - sku : BL394D + quantity : 4 + description : Basketball + price : 450.00 + - sku : BL4438H + quantity : 1 + description : Super Hoop + price : 2392.00 +tax : 251.42 +total: 4443.52 +comments: + Late afternoon is best. + Backup contact is Nancy + Billsmer @ 338-4338. + +# Another full-length example +--- +Time: 2001-11-23 15:01:42 -5 +User: ed +Warning: + This is an error message + for the log file +--- +Time: 2001-11-23 15:02:31 -5 +User: ed +Warning: + A slightly different error + message. +--- +Date: 2001-11-23 15:03:17 -5 +User: ed +Fatal: + Unknown variable "bar" +Stack: + - file: TopClass.py + line: 23 + code: | + x = MoreObject("345\n") + - file: MoreClass.py + line: 58 + code: |- + foo = bar + diff --git a/third_party/python/PyYAML/examples/pygments-lexer/yaml.py b/third_party/python/PyYAML/examples/pygments-lexer/yaml.py new file mode 100644 index 0000000000..1a1bbdeb3a --- /dev/null +++ b/third_party/python/PyYAML/examples/pygments-lexer/yaml.py @@ -0,0 +1,431 @@ + +""" +yaml.py + +Lexer for YAML, a human-friendly data serialization language +(http://yaml.org/). + +Written by Kirill Simonov . + +License: Whatever suitable for inclusion into the Pygments package. +""" + +from pygments.lexer import \ + ExtendedRegexLexer, LexerContext, include, bygroups +from pygments.token import \ + Text, Comment, Punctuation, Name, Literal + +__all__ = ['YAMLLexer'] + + +class YAMLLexerContext(LexerContext): + """Indentation context for the YAML lexer.""" + + def __init__(self, *args, **kwds): + super(YAMLLexerContext, self).__init__(*args, **kwds) + self.indent_stack = [] + self.indent = -1 + self.next_indent = 0 + self.block_scalar_indent = None + + +def something(TokenClass): + """Do not produce empty tokens.""" + def callback(lexer, match, context): + text = match.group() + if not text: + return + yield match.start(), TokenClass, text + context.pos = match.end() + return callback + +def reset_indent(TokenClass): + """Reset the indentation levels.""" + def callback(lexer, match, context): + text = match.group() + context.indent_stack = [] + context.indent = -1 + context.next_indent = 0 + context.block_scalar_indent = None + yield match.start(), TokenClass, text + context.pos = match.end() + return callback + +def save_indent(TokenClass, start=False): + """Save a possible indentation level.""" + def callback(lexer, match, context): + text = match.group() + extra = '' + if start: + context.next_indent = len(text) + if context.next_indent < context.indent: + while context.next_indent < context.indent: + context.indent = context.indent_stack.pop() + if context.next_indent > context.indent: + extra = text[context.indent:] + text = text[:context.indent] + else: + context.next_indent += len(text) + if text: + yield match.start(), TokenClass, text + if extra: + yield match.start()+len(text), TokenClass.Error, extra + context.pos = match.end() + return callback + +def set_indent(TokenClass, implicit=False): + """Set the previously saved indentation level.""" + def callback(lexer, match, context): + text = match.group() + if context.indent < context.next_indent: + context.indent_stack.append(context.indent) + context.indent = context.next_indent + if not implicit: + context.next_indent += len(text) + yield match.start(), TokenClass, text + context.pos = match.end() + return callback + +def set_block_scalar_indent(TokenClass): + """Set an explicit indentation level for a block scalar.""" + def callback(lexer, match, context): + text = match.group() + context.block_scalar_indent = None + if not text: + return + increment = match.group(1) + if increment: + current_indent = max(context.indent, 0) + increment = int(increment) + context.block_scalar_indent = current_indent + increment + if text: + yield match.start(), TokenClass, text + context.pos = match.end() + return callback + +def parse_block_scalar_empty_line(IndentTokenClass, ContentTokenClass): + """Process an empty line in a block scalar.""" + def callback(lexer, match, context): + text = match.group() + if (context.block_scalar_indent is None or + len(text) <= context.block_scalar_indent): + if text: + yield match.start(), IndentTokenClass, text + else: + indentation = text[:context.block_scalar_indent] + content = text[context.block_scalar_indent:] + yield match.start(), IndentTokenClass, indentation + yield (match.start()+context.block_scalar_indent, + ContentTokenClass, content) + context.pos = match.end() + return callback + +def parse_block_scalar_indent(TokenClass): + """Process indentation spaces in a block scalar.""" + def callback(lexer, match, context): + text = match.group() + if context.block_scalar_indent is None: + if len(text) <= max(context.indent, 0): + context.stack.pop() + context.stack.pop() + return + context.block_scalar_indent = len(text) + else: + if len(text) < context.block_scalar_indent: + context.stack.pop() + context.stack.pop() + return + if text: + yield match.start(), TokenClass, text + context.pos = match.end() + return callback + +def parse_plain_scalar_indent(TokenClass): + """Process indentation spaces in a plain scalar.""" + def callback(lexer, match, context): + text = match.group() + if len(text) <= context.indent: + context.stack.pop() + context.stack.pop() + return + if text: + yield match.start(), TokenClass, text + context.pos = match.end() + return callback + + +class YAMLLexer(ExtendedRegexLexer): + """Lexer for the YAML language.""" + + name = 'YAML' + aliases = ['yaml'] + filenames = ['*.yaml', '*.yml'] + mimetypes = ['text/x-yaml'] + + tokens = { + + # the root rules + 'root': [ + # ignored whitespaces + (r'[ ]+(?=#|$)', Text.Blank), + # line breaks + (r'\n+', Text.Break), + # a comment + (r'#[^\n]*', Comment.Single), + # the '%YAML' directive + (r'^%YAML(?=[ ]|$)', reset_indent(Name.Directive), + 'yaml-directive'), + # the %TAG directive + (r'^%TAG(?=[ ]|$)', reset_indent(Name.Directive), + 'tag-directive'), + # document start and document end indicators + (r'^(?:---|\.\.\.)(?=[ ]|$)', + reset_indent(Punctuation.Document), 'block-line'), + # indentation spaces + (r'[ ]*(?![ \t\n\r\f\v]|$)', + save_indent(Text.Indent, start=True), + ('block-line', 'indentation')), + ], + + # trailing whitespaces after directives or a block scalar indicator + 'ignored-line': [ + # ignored whitespaces + (r'[ ]+(?=#|$)', Text.Blank), + # a comment + (r'#[^\n]*', Comment.Single), + # line break + (r'\n', Text.Break, '#pop:2'), + ], + + # the %YAML directive + 'yaml-directive': [ + # the version number + (r'([ ]+)([0-9]+\.[0-9]+)', + bygroups(Text.Blank, Literal.Version), 'ignored-line'), + ], + + # the %YAG directive + 'tag-directive': [ + # a tag handle and the corresponding prefix + (r'([ ]+)(!|![0-9A-Za-z_-]*!)' + r'([ ]+)(!|!?[0-9A-Za-z;/?:@&=+$,_.!~*\'()\[\]%-]+)', + bygroups(Text.Blank, Name.Type, Text.Blank, Name.Type), + 'ignored-line'), + ], + + # block scalar indicators and indentation spaces + 'indentation': [ + # trailing whitespaces are ignored + (r'[ ]*$', something(Text.Blank), '#pop:2'), + # whitespaces preceding block collection indicators + (r'[ ]+(?=[?:-](?:[ ]|$))', save_indent(Text.Indent)), + # block collection indicators + (r'[?:-](?=[ ]|$)', set_indent(Punctuation.Indicator)), + # the beginning a block line + (r'[ ]*', save_indent(Text.Indent), '#pop'), + ], + + # an indented line in the block context + 'block-line': [ + # the line end + (r'[ ]*(?=#|$)', something(Text.Blank), '#pop'), + # whitespaces separating tokens + (r'[ ]+', Text.Blank), + # tags, anchors and aliases, + include('descriptors'), + # block collections and scalars + include('block-nodes'), + # flow collections and quoted scalars + include('flow-nodes'), + # a plain scalar + (r'(?=[^ \t\n\r\f\v?:,\[\]{}#&*!|>\'"%@`-]|[?:-][^ \t\n\r\f\v])', + something(Literal.Scalar.Plain), + 'plain-scalar-in-block-context'), + ], + + # tags, anchors, aliases + 'descriptors' : [ + # a full-form tag + (r'!<[0-9A-Za-z;/?:@&=+$,_.!~*\'()\[\]%-]+>', Name.Type), + # a tag in the form '!', '!suffix' or '!handle!suffix' + (r'!(?:[0-9A-Za-z_-]+)?' + r'(?:![0-9A-Za-z;/?:@&=+$,_.!~*\'()\[\]%-]+)?', Name.Type), + # an anchor + (r'&[0-9A-Za-z_-]+', Name.Anchor), + # an alias + (r'\*[0-9A-Za-z_-]+', Name.Alias), + ], + + # block collections and scalars + 'block-nodes': [ + # implicit key + (r':(?=[ ]|$)', set_indent(Punctuation.Indicator, implicit=True)), + # literal and folded scalars + (r'[|>]', Punctuation.Indicator, + ('block-scalar-content', 'block-scalar-header')), + ], + + # flow collections and quoted scalars + 'flow-nodes': [ + # a flow sequence + (r'\[', Punctuation.Indicator, 'flow-sequence'), + # a flow mapping + (r'\{', Punctuation.Indicator, 'flow-mapping'), + # a single-quoted scalar + (r'\'', Literal.Scalar.Flow.Quote, 'single-quoted-scalar'), + # a double-quoted scalar + (r'\"', Literal.Scalar.Flow.Quote, 'double-quoted-scalar'), + ], + + # the content of a flow collection + 'flow-collection': [ + # whitespaces + (r'[ ]+', Text.Blank), + # line breaks + (r'\n+', Text.Break), + # a comment + (r'#[^\n]*', Comment.Single), + # simple indicators + (r'[?:,]', Punctuation.Indicator), + # tags, anchors and aliases + include('descriptors'), + # nested collections and quoted scalars + include('flow-nodes'), + # a plain scalar + (r'(?=[^ \t\n\r\f\v?:,\[\]{}#&*!|>\'"%@`])', + something(Literal.Scalar.Plain), + 'plain-scalar-in-flow-context'), + ], + + # a flow sequence indicated by '[' and ']' + 'flow-sequence': [ + # include flow collection rules + include('flow-collection'), + # the closing indicator + (r'\]', Punctuation.Indicator, '#pop'), + ], + + # a flow mapping indicated by '{' and '}' + 'flow-mapping': [ + # include flow collection rules + include('flow-collection'), + # the closing indicator + (r'\}', Punctuation.Indicator, '#pop'), + ], + + # block scalar lines + 'block-scalar-content': [ + # line break + (r'\n', Text.Break), + # empty line + (r'^[ ]+$', + parse_block_scalar_empty_line(Text.Indent, + Literal.Scalar.Block)), + # indentation spaces (we may leave the state here) + (r'^[ ]*', parse_block_scalar_indent(Text.Indent)), + # line content + (r'[^\n\r\f\v]+', Literal.Scalar.Block), + ], + + # the content of a literal or folded scalar + 'block-scalar-header': [ + # indentation indicator followed by chomping flag + (r'([1-9])?[+-]?(?=[ ]|$)', + set_block_scalar_indent(Punctuation.Indicator), + 'ignored-line'), + # chomping flag followed by indentation indicator + (r'[+-]?([1-9])?(?=[ ]|$)', + set_block_scalar_indent(Punctuation.Indicator), + 'ignored-line'), + ], + + # ignored and regular whitespaces in quoted scalars + 'quoted-scalar-whitespaces': [ + # leading and trailing whitespaces are ignored + (r'^[ ]+|[ ]+$', Text.Blank), + # line breaks are ignored + (r'\n+', Text.Break), + # other whitespaces are a part of the value + (r'[ ]+', Literal.Scalar.Flow), + ], + + # single-quoted scalars + 'single-quoted-scalar': [ + # include whitespace and line break rules + include('quoted-scalar-whitespaces'), + # escaping of the quote character + (r'\'\'', Literal.Scalar.Flow.Escape), + # regular non-whitespace characters + (r'[^ \t\n\r\f\v\']+', Literal.Scalar.Flow), + # the closing quote + (r'\'', Literal.Scalar.Flow.Quote, '#pop'), + ], + + # double-quoted scalars + 'double-quoted-scalar': [ + # include whitespace and line break rules + include('quoted-scalar-whitespaces'), + # escaping of special characters + (r'\\[0abt\tn\nvfre "\\N_LP]', Literal.Scalar.Flow.Escape), + # escape codes + (r'\\(?:x[0-9A-Fa-f]{2}|u[0-9A-Fa-f]{4}|U[0-9A-Fa-f]{8})', + Literal.Scalar.Flow.Escape), + # regular non-whitespace characters + (r'[^ \t\n\r\f\v\"\\]+', Literal.Scalar.Flow), + # the closing quote + (r'"', Literal.Scalar.Flow.Quote, '#pop'), + ], + + # the beginning of a new line while scanning a plain scalar + 'plain-scalar-in-block-context-new-line': [ + # empty lines + (r'^[ ]+$', Text.Blank), + # line breaks + (r'\n+', Text.Break), + # document start and document end indicators + (r'^(?=---|\.\.\.)', something(Punctuation.Document), '#pop:3'), + # indentation spaces (we may leave the block line state here) + (r'^[ ]*', parse_plain_scalar_indent(Text.Indent), '#pop'), + ], + + # a plain scalar in the block context + 'plain-scalar-in-block-context': [ + # the scalar ends with the ':' indicator + (r'[ ]*(?=:[ ]|:$)', something(Text.Blank), '#pop'), + # the scalar ends with whitespaces followed by a comment + (r'[ ]+(?=#)', Text.Blank, '#pop'), + # trailing whitespaces are ignored + (r'[ ]+$', Text.Blank), + # line breaks are ignored + (r'\n+', Text.Break, 'plain-scalar-in-block-context-new-line'), + # other whitespaces are a part of the value + (r'[ ]+', Literal.Scalar.Plain), + # regular non-whitespace characters + (r'(?::(?![ \t\n\r\f\v])|[^ \t\n\r\f\v:])+', + Literal.Scalar.Plain), + ], + + # a plain scalar is the flow context + 'plain-scalar-in-flow-context': [ + # the scalar ends with an indicator character + (r'[ ]*(?=[,:?\[\]{}])', something(Text.Blank), '#pop'), + # the scalar ends with a comment + (r'[ ]+(?=#)', Text.Blank, '#pop'), + # leading and trailing whitespaces are ignored + (r'^[ ]+|[ ]+$', Text.Blank), + # line breaks are ignored + (r'\n+', Text.Break), + # other whitespaces are a part of the value + (r'[ ]+', Literal.Scalar.Plain), + # regular non-whitespace characters + (r'[^ \t\n\r\f\v,:?\[\]{}]+', Literal.Scalar.Plain), + ], + + } + + def get_tokens_unprocessed(self, text=None, context=None): + if context is None: + context = YAMLLexerContext(text, 0) + return super(YAMLLexer, self).get_tokens_unprocessed(text, context) + + diff --git a/third_party/python/PyYAML/examples/yaml-highlight/yaml_hl.cfg b/third_party/python/PyYAML/examples/yaml-highlight/yaml_hl.cfg new file mode 100644 index 0000000000..69bb847764 --- /dev/null +++ b/third_party/python/PyYAML/examples/yaml-highlight/yaml_hl.cfg @@ -0,0 +1,115 @@ +%YAML 1.1 +--- + +ascii: + + header: "\e[0;1;30;40m" + + footer: "\e[0m" + + tokens: + stream-start: + stream-end: + directive: { start: "\e[35m", end: "\e[0;1;30;40m" } + document-start: { start: "\e[35m", end: "\e[0;1;30;40m" } + document-end: { start: "\e[35m", end: "\e[0;1;30;40m" } + block-sequence-start: + block-mapping-start: + block-end: + flow-sequence-start: { start: "\e[33m", end: "\e[0;1;30;40m" } + flow-mapping-start: { start: "\e[33m", end: "\e[0;1;30;40m" } + flow-sequence-end: { start: "\e[33m", end: "\e[0;1;30;40m" } + flow-mapping-end: { start: "\e[33m", end: "\e[0;1;30;40m" } + key: { start: "\e[33m", end: "\e[0;1;30;40m" } + value: { start: "\e[33m", end: "\e[0;1;30;40m" } + block-entry: { start: "\e[33m", end: "\e[0;1;30;40m" } + flow-entry: { start: "\e[33m", end: "\e[0;1;30;40m" } + alias: { start: "\e[32m", end: "\e[0;1;30;40m" } + anchor: { start: "\e[32m", end: "\e[0;1;30;40m" } + tag: { start: "\e[32m", end: "\e[0;1;30;40m" } + scalar: { start: "\e[36m", end: "\e[0;1;30;40m" } + + replaces: + - "\r\n": "\n" + - "\r": "\n" + - "\n": "\n" + - "\x85": "\n" + - "\u2028": "\n" + - "\u2029": "\n" + +html: &html + + tokens: + stream-start: + stream-end: + directive: { start: , end: } + document-start: { start: , end: } + document-end: { start: , end: } + block-sequence-start: + block-mapping-start: + block-end: + flow-sequence-start: { start: , end: } + flow-mapping-start: { start: , end: } + flow-sequence-end: { start: , end: } + flow-mapping-end: { start: , end: } + key: { start: , end: } + value: { start: , end: } + block-entry: { start: , end: } + flow-entry: { start: , end: } + alias: { start: , end: } + anchor: { start: , end: } + tag: { start: , end: } + scalar: { start: , end: } + + events: + stream-start: { start: 
 }
+        stream-end:     { end:
} + document-start: { start: } + document-end: { end: } + sequence-start: { start: } + sequence-end: { end: } + mapping-start: { start: } + mapping-end: { end: } + scalar: { start: , end: } + + replaces: + - "\r\n": "\n" + - "\r": "\n" + - "\n": "\n" + - "\x85": "\n" + - "\u2028": "\n" + - "\u2029": "\n" + - "&": "&" + - "<": "<" + - ">": ">" + +html-page: + + header: | + + + A YAML stream + + + + footer: | + + + + <<: *html + + +# vim: ft=yaml diff --git a/third_party/python/PyYAML/examples/yaml-highlight/yaml_hl.py b/third_party/python/PyYAML/examples/yaml-highlight/yaml_hl.py new file mode 100755 index 0000000000..96e0ae7b1b --- /dev/null +++ b/third_party/python/PyYAML/examples/yaml-highlight/yaml_hl.py @@ -0,0 +1,114 @@ +#!/usr/bin/python + +import yaml, codecs, sys, os.path, optparse + +class Style: + + def __init__(self, header=None, footer=None, + tokens=None, events=None, replaces=None): + self.header = header + self.footer = footer + self.replaces = replaces + self.substitutions = {} + for domain, Class in [(tokens, 'Token'), (events, 'Event')]: + if not domain: + continue + for key in domain: + name = ''.join([part.capitalize() for part in key.split('-')]) + cls = getattr(yaml, '%s%s' % (name, Class)) + value = domain[key] + if not value: + continue + start = value.get('start') + end = value.get('end') + if start: + self.substitutions[cls, -1] = start + if end: + self.substitutions[cls, +1] = end + + def __setstate__(self, state): + self.__init__(**state) + +yaml.add_path_resolver(u'tag:yaml.org,2002:python/object:__main__.Style', + [None], dict) +yaml.add_path_resolver(u'tag:yaml.org,2002:pairs', + [None, u'replaces'], list) + +class YAMLHighlight: + + def __init__(self, options): + config = yaml.full_load(file(options.config, 'rb').read()) + self.style = config[options.style] + if options.input: + self.input = file(options.input, 'rb') + else: + self.input = sys.stdin + if options.output: + self.output = file(options.output, 'wb') + else: + self.output = sys.stdout + + def highlight(self): + input = self.input.read() + if input.startswith(codecs.BOM_UTF16_LE): + input = unicode(input, 'utf-16-le') + elif input.startswith(codecs.BOM_UTF16_BE): + input = unicode(input, 'utf-16-be') + else: + input = unicode(input, 'utf-8') + substitutions = self.style.substitutions + tokens = yaml.scan(input) + events = yaml.parse(input) + markers = [] + number = 0 + for token in tokens: + number += 1 + if token.start_mark.index != token.end_mark.index: + cls = token.__class__ + if (cls, -1) in substitutions: + markers.append([token.start_mark.index, +2, number, substitutions[cls, -1]]) + if (cls, +1) in substitutions: + markers.append([token.end_mark.index, -2, number, substitutions[cls, +1]]) + number = 0 + for event in events: + number += 1 + cls = event.__class__ + if (cls, -1) in substitutions: + markers.append([event.start_mark.index, +1, number, substitutions[cls, -1]]) + if (cls, +1) in substitutions: + markers.append([event.end_mark.index, -1, number, substitutions[cls, +1]]) + markers.sort() + markers.reverse() + chunks = [] + position = len(input) + for index, weight1, weight2, substitution in markers: + if index < position: + chunk = input[index:position] + for substring, replacement in self.style.replaces: + chunk = chunk.replace(substring, replacement) + chunks.append(chunk) + position = index + chunks.append(substitution) + chunks.reverse() + result = u''.join(chunks) + if self.style.header: + self.output.write(self.style.header) + self.output.write(result.encode('utf-8')) + if self.style.footer: + self.output.write(self.style.footer) + +if __name__ == '__main__': + parser = optparse.OptionParser() + parser.add_option('-s', '--style', dest='style', default='ascii', + help="specify the highlighting style", metavar='STYLE') + parser.add_option('-c', '--config', dest='config', + default=os.path.join(os.path.dirname(sys.argv[0]), 'yaml_hl.cfg'), + help="set an alternative configuration file", metavar='CONFIG') + parser.add_option('-i', '--input', dest='input', default=None, + help="set the input file (default: stdin)", metavar='FILE') + parser.add_option('-o', '--output', dest='output', default=None, + help="set the output file (default: stdout)", metavar='FILE') + (options, args) = parser.parse_args() + hl = YAMLHighlight(options) + hl.highlight() + diff --git a/third_party/python/PyYAML/lib/_yaml/__init__.py b/third_party/python/PyYAML/lib/_yaml/__init__.py new file mode 100644 index 0000000000..7baa8c4b68 --- /dev/null +++ b/third_party/python/PyYAML/lib/_yaml/__init__.py @@ -0,0 +1,33 @@ +# This is a stub package designed to roughly emulate the _yaml +# extension module, which previously existed as a standalone module +# and has been moved into the `yaml` package namespace. +# It does not perfectly mimic its old counterpart, but should get +# close enough for anyone who's relying on it even when they shouldn't. +import yaml + +# in some circumstances, the yaml module we imoprted may be from a different version, so we need +# to tread carefully when poking at it here (it may not have the attributes we expect) +if not getattr(yaml, '__with_libyaml__', False): + from sys import version_info + + exc = ModuleNotFoundError if version_info >= (3, 6) else ImportError + raise exc("No module named '_yaml'") +else: + from yaml._yaml import * + import warnings + warnings.warn( + 'The _yaml extension module is now located at yaml._yaml' + ' and its location is subject to change. To use the' + ' LibYAML-based parser and emitter, import from `yaml`:' + ' `from yaml import CLoader as Loader, CDumper as Dumper`.', + DeprecationWarning + ) + del warnings + # Don't `del yaml` here because yaml is actually an existing + # namespace member of _yaml. + +__name__ = '_yaml' +# If the module is top-level (i.e. not a part of any specific package) +# then the attribute should be set to ''. +# https://docs.python.org/3.8/library/types.html +__package__ = '' diff --git a/third_party/python/PyYAML/lib/yaml/__init__.py b/third_party/python/PyYAML/lib/yaml/__init__.py new file mode 100644 index 0000000000..3c988198d5 --- /dev/null +++ b/third_party/python/PyYAML/lib/yaml/__init__.py @@ -0,0 +1,431 @@ + +from error import * + +from tokens import * +from events import * +from nodes import * + +from loader import * +from dumper import * + +__version__ = '5.4.1' + +try: + from cyaml import * + __with_libyaml__ = True +except ImportError: + __with_libyaml__ = False + + +#------------------------------------------------------------------------------ +# Warnings control +#------------------------------------------------------------------------------ + +# 'Global' warnings state: +_warnings_enabled = { + 'YAMLLoadWarning': True, +} + +# Get or set global warnings' state +def warnings(settings=None): + if settings is None: + return _warnings_enabled + + if type(settings) is dict: + for key in settings: + if key in _warnings_enabled: + _warnings_enabled[key] = settings[key] + +# Warn when load() is called without Loader=... +class YAMLLoadWarning(RuntimeWarning): + pass + +def load_warning(method): + if _warnings_enabled['YAMLLoadWarning'] is False: + return + + import warnings + + message = ( + "calling yaml.%s() without Loader=... is deprecated, as the " + "default Loader is unsafe. Please read " + "https://msg.pyyaml.org/load for full details." + ) % method + + warnings.warn(message, YAMLLoadWarning, stacklevel=3) + +#------------------------------------------------------------------------------ +def scan(stream, Loader=Loader): + """ + Scan a YAML stream and produce scanning tokens. + """ + loader = Loader(stream) + try: + while loader.check_token(): + yield loader.get_token() + finally: + loader.dispose() + +def parse(stream, Loader=Loader): + """ + Parse a YAML stream and produce parsing events. + """ + loader = Loader(stream) + try: + while loader.check_event(): + yield loader.get_event() + finally: + loader.dispose() + +def compose(stream, Loader=Loader): + """ + Parse the first YAML document in a stream + and produce the corresponding representation tree. + """ + loader = Loader(stream) + try: + return loader.get_single_node() + finally: + loader.dispose() + +def compose_all(stream, Loader=Loader): + """ + Parse all YAML documents in a stream + and produce corresponding representation trees. + """ + loader = Loader(stream) + try: + while loader.check_node(): + yield loader.get_node() + finally: + loader.dispose() + +def load(stream, Loader=None): + """ + Parse the first YAML document in a stream + and produce the corresponding Python object. + """ + if Loader is None: + load_warning('load') + Loader = FullLoader + + loader = Loader(stream) + try: + return loader.get_single_data() + finally: + loader.dispose() + +def load_all(stream, Loader=None): + """ + Parse all YAML documents in a stream + and produce corresponding Python objects. + """ + if Loader is None: + load_warning('load_all') + Loader = FullLoader + + loader = Loader(stream) + try: + while loader.check_data(): + yield loader.get_data() + finally: + loader.dispose() + +def full_load(stream): + """ + Parse the first YAML document in a stream + and produce the corresponding Python object. + + Resolve all tags except those known to be + unsafe on untrusted input. + """ + return load(stream, FullLoader) + +def full_load_all(stream): + """ + Parse all YAML documents in a stream + and produce corresponding Python objects. + + Resolve all tags except those known to be + unsafe on untrusted input. + """ + return load_all(stream, FullLoader) + +def safe_load(stream): + """ + Parse the first YAML document in a stream + and produce the corresponding Python object. + + Resolve only basic YAML tags. This is known + to be safe for untrusted input. + """ + return load(stream, SafeLoader) + +def safe_load_all(stream): + """ + Parse all YAML documents in a stream + and produce corresponding Python objects. + + Resolve only basic YAML tags. This is known + to be safe for untrusted input. + """ + return load_all(stream, SafeLoader) + +def unsafe_load(stream): + """ + Parse the first YAML document in a stream + and produce the corresponding Python object. + + Resolve all tags, even those known to be + unsafe on untrusted input. + """ + return load(stream, UnsafeLoader) + +def unsafe_load_all(stream): + """ + Parse all YAML documents in a stream + and produce corresponding Python objects. + + Resolve all tags, even those known to be + unsafe on untrusted input. + """ + return load_all(stream, UnsafeLoader) + +def emit(events, stream=None, Dumper=Dumper, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None): + """ + Emit YAML parsing events into a stream. + If stream is None, return the produced string instead. + """ + getvalue = None + if stream is None: + from StringIO import StringIO + stream = StringIO() + getvalue = stream.getvalue + dumper = Dumper(stream, canonical=canonical, indent=indent, width=width, + allow_unicode=allow_unicode, line_break=line_break) + try: + for event in events: + dumper.emit(event) + finally: + dumper.dispose() + if getvalue: + return getvalue() + +def serialize_all(nodes, stream=None, Dumper=Dumper, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding='utf-8', explicit_start=None, explicit_end=None, + version=None, tags=None): + """ + Serialize a sequence of representation trees into a YAML stream. + If stream is None, return the produced string instead. + """ + getvalue = None + if stream is None: + if encoding is None: + from StringIO import StringIO + else: + from cStringIO import StringIO + stream = StringIO() + getvalue = stream.getvalue + dumper = Dumper(stream, canonical=canonical, indent=indent, width=width, + allow_unicode=allow_unicode, line_break=line_break, + encoding=encoding, version=version, tags=tags, + explicit_start=explicit_start, explicit_end=explicit_end) + try: + dumper.open() + for node in nodes: + dumper.serialize(node) + dumper.close() + finally: + dumper.dispose() + if getvalue: + return getvalue() + +def serialize(node, stream=None, Dumper=Dumper, **kwds): + """ + Serialize a representation tree into a YAML stream. + If stream is None, return the produced string instead. + """ + return serialize_all([node], stream, Dumper=Dumper, **kwds) + +def dump_all(documents, stream=None, Dumper=Dumper, + default_style=None, default_flow_style=False, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding='utf-8', explicit_start=None, explicit_end=None, + version=None, tags=None, sort_keys=True): + """ + Serialize a sequence of Python objects into a YAML stream. + If stream is None, return the produced string instead. + """ + getvalue = None + if stream is None: + if encoding is None: + from StringIO import StringIO + else: + from cStringIO import StringIO + stream = StringIO() + getvalue = stream.getvalue + dumper = Dumper(stream, default_style=default_style, + default_flow_style=default_flow_style, + canonical=canonical, indent=indent, width=width, + allow_unicode=allow_unicode, line_break=line_break, + encoding=encoding, version=version, tags=tags, + explicit_start=explicit_start, explicit_end=explicit_end, sort_keys=sort_keys) + try: + dumper.open() + for data in documents: + dumper.represent(data) + dumper.close() + finally: + dumper.dispose() + if getvalue: + return getvalue() + +def dump(data, stream=None, Dumper=Dumper, **kwds): + """ + Serialize a Python object into a YAML stream. + If stream is None, return the produced string instead. + """ + return dump_all([data], stream, Dumper=Dumper, **kwds) + +def safe_dump_all(documents, stream=None, **kwds): + """ + Serialize a sequence of Python objects into a YAML stream. + Produce only basic YAML tags. + If stream is None, return the produced string instead. + """ + return dump_all(documents, stream, Dumper=SafeDumper, **kwds) + +def safe_dump(data, stream=None, **kwds): + """ + Serialize a Python object into a YAML stream. + Produce only basic YAML tags. + If stream is None, return the produced string instead. + """ + return dump_all([data], stream, Dumper=SafeDumper, **kwds) + +def add_implicit_resolver(tag, regexp, first=None, + Loader=None, Dumper=Dumper): + """ + Add an implicit scalar detector. + If an implicit scalar value matches the given regexp, + the corresponding tag is assigned to the scalar. + first is a sequence of possible initial characters or None. + """ + if Loader is None: + loader.Loader.add_implicit_resolver(tag, regexp, first) + loader.FullLoader.add_implicit_resolver(tag, regexp, first) + loader.UnsafeLoader.add_implicit_resolver(tag, regexp, first) + else: + Loader.add_implicit_resolver(tag, regexp, first) + Dumper.add_implicit_resolver(tag, regexp, first) + +def add_path_resolver(tag, path, kind=None, Loader=None, Dumper=Dumper): + """ + Add a path based resolver for the given tag. + A path is a list of keys that forms a path + to a node in the representation tree. + Keys can be string values, integers, or None. + """ + if Loader is None: + loader.Loader.add_path_resolver(tag, path, kind) + loader.FullLoader.add_path_resolver(tag, path, kind) + loader.UnsafeLoader.add_path_resolver(tag, path, kind) + else: + Loader.add_path_resolver(tag, path, kind) + Dumper.add_path_resolver(tag, path, kind) + +def add_constructor(tag, constructor, Loader=None): + """ + Add a constructor for the given tag. + Constructor is a function that accepts a Loader instance + and a node object and produces the corresponding Python object. + """ + if Loader is None: + loader.Loader.add_constructor(tag, constructor) + loader.FullLoader.add_constructor(tag, constructor) + loader.UnsafeLoader.add_constructor(tag, constructor) + else: + Loader.add_constructor(tag, constructor) + +def add_multi_constructor(tag_prefix, multi_constructor, Loader=None): + """ + Add a multi-constructor for the given tag prefix. + Multi-constructor is called for a node if its tag starts with tag_prefix. + Multi-constructor accepts a Loader instance, a tag suffix, + and a node object and produces the corresponding Python object. + """ + if Loader is None: + loader.Loader.add_multi_constructor(tag_prefix, multi_constructor) + loader.FullLoader.add_multi_constructor(tag_prefix, multi_constructor) + loader.UnsafeLoader.add_multi_constructor(tag_prefix, multi_constructor) + else: + Loader.add_multi_constructor(tag_prefix, multi_constructor) + +def add_representer(data_type, representer, Dumper=Dumper): + """ + Add a representer for the given type. + Representer is a function accepting a Dumper instance + and an instance of the given data type + and producing the corresponding representation node. + """ + Dumper.add_representer(data_type, representer) + +def add_multi_representer(data_type, multi_representer, Dumper=Dumper): + """ + Add a representer for the given type. + Multi-representer is a function accepting a Dumper instance + and an instance of the given data type or subtype + and producing the corresponding representation node. + """ + Dumper.add_multi_representer(data_type, multi_representer) + +class YAMLObjectMetaclass(type): + """ + The metaclass for YAMLObject. + """ + def __init__(cls, name, bases, kwds): + super(YAMLObjectMetaclass, cls).__init__(name, bases, kwds) + if 'yaml_tag' in kwds and kwds['yaml_tag'] is not None: + if isinstance(cls.yaml_loader, list): + for loader in cls.yaml_loader: + loader.add_constructor(cls.yaml_tag, cls.from_yaml) + else: + cls.yaml_loader.add_constructor(cls.yaml_tag, cls.from_yaml) + + cls.yaml_dumper.add_representer(cls, cls.to_yaml) + +class YAMLObject(object): + """ + An object that can dump itself to a YAML stream + and load itself from a YAML stream. + """ + + __metaclass__ = YAMLObjectMetaclass + __slots__ = () # no direct instantiation, so allow immutable subclasses + + yaml_loader = [Loader, FullLoader, UnsafeLoader] + yaml_dumper = Dumper + + yaml_tag = None + yaml_flow_style = None + + def from_yaml(cls, loader, node): + """ + Convert a representation node to a Python object. + """ + return loader.construct_yaml_object(node, cls) + from_yaml = classmethod(from_yaml) + + def to_yaml(cls, dumper, data): + """ + Convert a Python object to a representation node. + """ + return dumper.represent_yaml_object(cls.yaml_tag, data, cls, + flow_style=cls.yaml_flow_style) + to_yaml = classmethod(to_yaml) + diff --git a/third_party/python/PyYAML/lib/yaml/composer.py b/third_party/python/PyYAML/lib/yaml/composer.py new file mode 100644 index 0000000000..df85ef653b --- /dev/null +++ b/third_party/python/PyYAML/lib/yaml/composer.py @@ -0,0 +1,139 @@ + +__all__ = ['Composer', 'ComposerError'] + +from error import MarkedYAMLError +from events import * +from nodes import * + +class ComposerError(MarkedYAMLError): + pass + +class Composer(object): + + def __init__(self): + self.anchors = {} + + def check_node(self): + # Drop the STREAM-START event. + if self.check_event(StreamStartEvent): + self.get_event() + + # If there are more documents available? + return not self.check_event(StreamEndEvent) + + def get_node(self): + # Get the root node of the next document. + if not self.check_event(StreamEndEvent): + return self.compose_document() + + def get_single_node(self): + # Drop the STREAM-START event. + self.get_event() + + # Compose a document if the stream is not empty. + document = None + if not self.check_event(StreamEndEvent): + document = self.compose_document() + + # Ensure that the stream contains no more documents. + if not self.check_event(StreamEndEvent): + event = self.get_event() + raise ComposerError("expected a single document in the stream", + document.start_mark, "but found another document", + event.start_mark) + + # Drop the STREAM-END event. + self.get_event() + + return document + + def compose_document(self): + # Drop the DOCUMENT-START event. + self.get_event() + + # Compose the root node. + node = self.compose_node(None, None) + + # Drop the DOCUMENT-END event. + self.get_event() + + self.anchors = {} + return node + + def compose_node(self, parent, index): + if self.check_event(AliasEvent): + event = self.get_event() + anchor = event.anchor + if anchor not in self.anchors: + raise ComposerError(None, None, "found undefined alias %r" + % anchor.encode('utf-8'), event.start_mark) + return self.anchors[anchor] + event = self.peek_event() + anchor = event.anchor + if anchor is not None: + if anchor in self.anchors: + raise ComposerError("found duplicate anchor %r; first occurrence" + % anchor.encode('utf-8'), self.anchors[anchor].start_mark, + "second occurrence", event.start_mark) + self.descend_resolver(parent, index) + if self.check_event(ScalarEvent): + node = self.compose_scalar_node(anchor) + elif self.check_event(SequenceStartEvent): + node = self.compose_sequence_node(anchor) + elif self.check_event(MappingStartEvent): + node = self.compose_mapping_node(anchor) + self.ascend_resolver() + return node + + def compose_scalar_node(self, anchor): + event = self.get_event() + tag = event.tag + if tag is None or tag == u'!': + tag = self.resolve(ScalarNode, event.value, event.implicit) + node = ScalarNode(tag, event.value, + event.start_mark, event.end_mark, style=event.style) + if anchor is not None: + self.anchors[anchor] = node + return node + + def compose_sequence_node(self, anchor): + start_event = self.get_event() + tag = start_event.tag + if tag is None or tag == u'!': + tag = self.resolve(SequenceNode, None, start_event.implicit) + node = SequenceNode(tag, [], + start_event.start_mark, None, + flow_style=start_event.flow_style) + if anchor is not None: + self.anchors[anchor] = node + index = 0 + while not self.check_event(SequenceEndEvent): + node.value.append(self.compose_node(node, index)) + index += 1 + end_event = self.get_event() + node.end_mark = end_event.end_mark + return node + + def compose_mapping_node(self, anchor): + start_event = self.get_event() + tag = start_event.tag + if tag is None or tag == u'!': + tag = self.resolve(MappingNode, None, start_event.implicit) + node = MappingNode(tag, [], + start_event.start_mark, None, + flow_style=start_event.flow_style) + if anchor is not None: + self.anchors[anchor] = node + while not self.check_event(MappingEndEvent): + #key_event = self.peek_event() + item_key = self.compose_node(node, None) + #if item_key in node.value: + # raise ComposerError("while composing a mapping", start_event.start_mark, + # "found duplicate key", key_event.start_mark) + item_value = self.compose_node(node, item_key) + #node.value[item_key] = item_value + node.value.append((item_key, item_value)) + end_event = self.get_event() + node.end_mark = end_event.end_mark + return node + diff --git a/third_party/python/PyYAML/lib/yaml/constructor.py b/third_party/python/PyYAML/lib/yaml/constructor.py new file mode 100644 index 0000000000..ff4e36828e --- /dev/null +++ b/third_party/python/PyYAML/lib/yaml/constructor.py @@ -0,0 +1,766 @@ + +__all__ = [ + 'BaseConstructor', + 'SafeConstructor', + 'FullConstructor', + 'UnsafeConstructor', + 'Constructor', + 'ConstructorError' +] + +from error import * +from nodes import * + +import datetime + +import binascii, re, sys, types + +class ConstructorError(MarkedYAMLError): + pass + + +class timezone(datetime.tzinfo): + def __init__(self, offset): + self._offset = offset + seconds = abs(offset).total_seconds() + self._name = 'UTC%s%02d:%02d' % ( + '-' if offset.days < 0 else '+', + seconds // 3600, + seconds % 3600 // 60 + ) + + def tzname(self, dt=None): + return self._name + + def utcoffset(self, dt=None): + return self._offset + + def dst(self, dt=None): + return datetime.timedelta(0) + + def __copy__(self): + return self.__deepcopy__() + + def __deepcopy__(self, memodict={}): + return self.__class__(self.utcoffset()) + + __repr__ = __str__ = tzname + + +class BaseConstructor(object): + + yaml_constructors = {} + yaml_multi_constructors = {} + + def __init__(self): + self.constructed_objects = {} + self.recursive_objects = {} + self.state_generators = [] + self.deep_construct = False + + def check_data(self): + # If there are more documents available? + return self.check_node() + + def check_state_key(self, key): + """Block special attributes/methods from being set in a newly created + object, to prevent user-controlled methods from being called during + deserialization""" + if self.get_state_keys_blacklist_regexp().match(key): + raise ConstructorError(None, None, + "blacklisted key '%s' in instance state found" % (key,), None) + + def get_data(self): + # Construct and return the next document. + if self.check_node(): + return self.construct_document(self.get_node()) + + def get_single_data(self): + # Ensure that the stream contains a single document and construct it. + node = self.get_single_node() + if node is not None: + return self.construct_document(node) + return None + + def construct_document(self, node): + data = self.construct_object(node) + while self.state_generators: + state_generators = self.state_generators + self.state_generators = [] + for generator in state_generators: + for dummy in generator: + pass + self.constructed_objects = {} + self.recursive_objects = {} + self.deep_construct = False + return data + + def construct_object(self, node, deep=False): + if node in self.constructed_objects: + return self.constructed_objects[node] + if deep: + old_deep = self.deep_construct + self.deep_construct = True + if node in self.recursive_objects: + raise ConstructorError(None, None, + "found unconstructable recursive node", node.start_mark) + self.recursive_objects[node] = None + constructor = None + tag_suffix = None + if node.tag in self.yaml_constructors: + constructor = self.yaml_constructors[node.tag] + else: + for tag_prefix in self.yaml_multi_constructors: + if tag_prefix is not None and node.tag.startswith(tag_prefix): + tag_suffix = node.tag[len(tag_prefix):] + constructor = self.yaml_multi_constructors[tag_prefix] + break + else: + if None in self.yaml_multi_constructors: + tag_suffix = node.tag + constructor = self.yaml_multi_constructors[None] + elif None in self.yaml_constructors: + constructor = self.yaml_constructors[None] + elif isinstance(node, ScalarNode): + constructor = self.__class__.construct_scalar + elif isinstance(node, SequenceNode): + constructor = self.__class__.construct_sequence + elif isinstance(node, MappingNode): + constructor = self.__class__.construct_mapping + if tag_suffix is None: + data = constructor(self, node) + else: + data = constructor(self, tag_suffix, node) + if isinstance(data, types.GeneratorType): + generator = data + data = generator.next() + if self.deep_construct: + for dummy in generator: + pass + else: + self.state_generators.append(generator) + self.constructed_objects[node] = data + del self.recursive_objects[node] + if deep: + self.deep_construct = old_deep + return data + + def construct_scalar(self, node): + if not isinstance(node, ScalarNode): + raise ConstructorError(None, None, + "expected a scalar node, but found %s" % node.id, + node.start_mark) + return node.value + + def construct_sequence(self, node, deep=False): + if not isinstance(node, SequenceNode): + raise ConstructorError(None, None, + "expected a sequence node, but found %s" % node.id, + node.start_mark) + return [self.construct_object(child, deep=deep) + for child in node.value] + + def construct_mapping(self, node, deep=False): + if not isinstance(node, MappingNode): + raise ConstructorError(None, None, + "expected a mapping node, but found %s" % node.id, + node.start_mark) + mapping = {} + for key_node, value_node in node.value: + key = self.construct_object(key_node, deep=deep) + try: + hash(key) + except TypeError, exc: + raise ConstructorError("while constructing a mapping", node.start_mark, + "found unacceptable key (%s)" % exc, key_node.start_mark) + value = self.construct_object(value_node, deep=deep) + mapping[key] = value + return mapping + + def construct_pairs(self, node, deep=False): + if not isinstance(node, MappingNode): + raise ConstructorError(None, None, + "expected a mapping node, but found %s" % node.id, + node.start_mark) + pairs = [] + for key_node, value_node in node.value: + key = self.construct_object(key_node, deep=deep) + value = self.construct_object(value_node, deep=deep) + pairs.append((key, value)) + return pairs + + def add_constructor(cls, tag, constructor): + if not 'yaml_constructors' in cls.__dict__: + cls.yaml_constructors = cls.yaml_constructors.copy() + cls.yaml_constructors[tag] = constructor + add_constructor = classmethod(add_constructor) + + def add_multi_constructor(cls, tag_prefix, multi_constructor): + if not 'yaml_multi_constructors' in cls.__dict__: + cls.yaml_multi_constructors = cls.yaml_multi_constructors.copy() + cls.yaml_multi_constructors[tag_prefix] = multi_constructor + add_multi_constructor = classmethod(add_multi_constructor) + +class SafeConstructor(BaseConstructor): + + def construct_scalar(self, node): + if isinstance(node, MappingNode): + for key_node, value_node in node.value: + if key_node.tag == u'tag:yaml.org,2002:value': + return self.construct_scalar(value_node) + return BaseConstructor.construct_scalar(self, node) + + def flatten_mapping(self, node): + merge = [] + index = 0 + while index < len(node.value): + key_node, value_node = node.value[index] + if key_node.tag == u'tag:yaml.org,2002:merge': + del node.value[index] + if isinstance(value_node, MappingNode): + self.flatten_mapping(value_node) + merge.extend(value_node.value) + elif isinstance(value_node, SequenceNode): + submerge = [] + for subnode in value_node.value: + if not isinstance(subnode, MappingNode): + raise ConstructorError("while constructing a mapping", + node.start_mark, + "expected a mapping for merging, but found %s" + % subnode.id, subnode.start_mark) + self.flatten_mapping(subnode) + submerge.append(subnode.value) + submerge.reverse() + for value in submerge: + merge.extend(value) + else: + raise ConstructorError("while constructing a mapping", node.start_mark, + "expected a mapping or list of mappings for merging, but found %s" + % value_node.id, value_node.start_mark) + elif key_node.tag == u'tag:yaml.org,2002:value': + key_node.tag = u'tag:yaml.org,2002:str' + index += 1 + else: + index += 1 + if merge: + node.value = merge + node.value + + def construct_mapping(self, node, deep=False): + if isinstance(node, MappingNode): + self.flatten_mapping(node) + return BaseConstructor.construct_mapping(self, node, deep=deep) + + def construct_yaml_null(self, node): + self.construct_scalar(node) + return None + + bool_values = { + u'yes': True, + u'no': False, + u'true': True, + u'false': False, + u'on': True, + u'off': False, + } + + def construct_yaml_bool(self, node): + value = self.construct_scalar(node) + return self.bool_values[value.lower()] + + def construct_yaml_int(self, node): + value = str(self.construct_scalar(node)) + value = value.replace('_', '') + sign = +1 + if value[0] == '-': + sign = -1 + if value[0] in '+-': + value = value[1:] + if value == '0': + return 0 + elif value.startswith('0b'): + return sign*int(value[2:], 2) + elif value.startswith('0x'): + return sign*int(value[2:], 16) + elif value[0] == '0': + return sign*int(value, 8) + elif ':' in value: + digits = [int(part) for part in value.split(':')] + digits.reverse() + base = 1 + value = 0 + for digit in digits: + value += digit*base + base *= 60 + return sign*value + else: + return sign*int(value) + + inf_value = 1e300 + while inf_value != inf_value*inf_value: + inf_value *= inf_value + nan_value = -inf_value/inf_value # Trying to make a quiet NaN (like C99). + + def construct_yaml_float(self, node): + value = str(self.construct_scalar(node)) + value = value.replace('_', '').lower() + sign = +1 + if value[0] == '-': + sign = -1 + if value[0] in '+-': + value = value[1:] + if value == '.inf': + return sign*self.inf_value + elif value == '.nan': + return self.nan_value + elif ':' in value: + digits = [float(part) for part in value.split(':')] + digits.reverse() + base = 1 + value = 0.0 + for digit in digits: + value += digit*base + base *= 60 + return sign*value + else: + return sign*float(value) + + def construct_yaml_binary(self, node): + value = self.construct_scalar(node) + try: + return str(value).decode('base64') + except (binascii.Error, UnicodeEncodeError), exc: + raise ConstructorError(None, None, + "failed to decode base64 data: %s" % exc, node.start_mark) + + timestamp_regexp = re.compile( + ur'''^(?P[0-9][0-9][0-9][0-9]) + -(?P[0-9][0-9]?) + -(?P[0-9][0-9]?) + (?:(?:[Tt]|[ \t]+) + (?P[0-9][0-9]?) + :(?P[0-9][0-9]) + :(?P[0-9][0-9]) + (?:\.(?P[0-9]*))? + (?:[ \t]*(?PZ|(?P[-+])(?P[0-9][0-9]?) + (?::(?P[0-9][0-9]))?))?)?$''', re.X) + + def construct_yaml_timestamp(self, node): + value = self.construct_scalar(node) + match = self.timestamp_regexp.match(node.value) + values = match.groupdict() + year = int(values['year']) + month = int(values['month']) + day = int(values['day']) + if not values['hour']: + return datetime.date(year, month, day) + hour = int(values['hour']) + minute = int(values['minute']) + second = int(values['second']) + fraction = 0 + tzinfo = None + if values['fraction']: + fraction = values['fraction'][:6] + while len(fraction) < 6: + fraction += '0' + fraction = int(fraction) + if values['tz_sign']: + tz_hour = int(values['tz_hour']) + tz_minute = int(values['tz_minute'] or 0) + delta = datetime.timedelta(hours=tz_hour, minutes=tz_minute) + if values['tz_sign'] == '-': + delta = -delta + tzinfo = timezone(delta) + elif values['tz']: + tzinfo = timezone(datetime.timedelta(0)) + return datetime.datetime(year, month, day, hour, minute, second, fraction, + tzinfo=tzinfo) + + def construct_yaml_omap(self, node): + # Note: we do not check for duplicate keys, because it's too + # CPU-expensive. + omap = [] + yield omap + if not isinstance(node, SequenceNode): + raise ConstructorError("while constructing an ordered map", node.start_mark, + "expected a sequence, but found %s" % node.id, node.start_mark) + for subnode in node.value: + if not isinstance(subnode, MappingNode): + raise ConstructorError("while constructing an ordered map", node.start_mark, + "expected a mapping of length 1, but found %s" % subnode.id, + subnode.start_mark) + if len(subnode.value) != 1: + raise ConstructorError("while constructing an ordered map", node.start_mark, + "expected a single mapping item, but found %d items" % len(subnode.value), + subnode.start_mark) + key_node, value_node = subnode.value[0] + key = self.construct_object(key_node) + value = self.construct_object(value_node) + omap.append((key, value)) + + def construct_yaml_pairs(self, node): + # Note: the same code as `construct_yaml_omap`. + pairs = [] + yield pairs + if not isinstance(node, SequenceNode): + raise ConstructorError("while constructing pairs", node.start_mark, + "expected a sequence, but found %s" % node.id, node.start_mark) + for subnode in node.value: + if not isinstance(subnode, MappingNode): + raise ConstructorError("while constructing pairs", node.start_mark, + "expected a mapping of length 1, but found %s" % subnode.id, + subnode.start_mark) + if len(subnode.value) != 1: + raise ConstructorError("while constructing pairs", node.start_mark, + "expected a single mapping item, but found %d items" % len(subnode.value), + subnode.start_mark) + key_node, value_node = subnode.value[0] + key = self.construct_object(key_node) + value = self.construct_object(value_node) + pairs.append((key, value)) + + def construct_yaml_set(self, node): + data = set() + yield data + value = self.construct_mapping(node) + data.update(value) + + def construct_yaml_str(self, node): + value = self.construct_scalar(node) + try: + return value.encode('ascii') + except UnicodeEncodeError: + return value + + def construct_yaml_seq(self, node): + data = [] + yield data + data.extend(self.construct_sequence(node)) + + def construct_yaml_map(self, node): + data = {} + yield data + value = self.construct_mapping(node) + data.update(value) + + def construct_yaml_object(self, node, cls): + data = cls.__new__(cls) + yield data + if hasattr(data, '__setstate__'): + state = self.construct_mapping(node, deep=True) + data.__setstate__(state) + else: + state = self.construct_mapping(node) + data.__dict__.update(state) + + def construct_undefined(self, node): + raise ConstructorError(None, None, + "could not determine a constructor for the tag %r" % node.tag.encode('utf-8'), + node.start_mark) + +SafeConstructor.add_constructor( + u'tag:yaml.org,2002:null', + SafeConstructor.construct_yaml_null) + +SafeConstructor.add_constructor( + u'tag:yaml.org,2002:bool', + SafeConstructor.construct_yaml_bool) + +SafeConstructor.add_constructor( + u'tag:yaml.org,2002:int', + SafeConstructor.construct_yaml_int) + +SafeConstructor.add_constructor( + u'tag:yaml.org,2002:float', + SafeConstructor.construct_yaml_float) + +SafeConstructor.add_constructor( + u'tag:yaml.org,2002:binary', + SafeConstructor.construct_yaml_binary) + +SafeConstructor.add_constructor( + u'tag:yaml.org,2002:timestamp', + SafeConstructor.construct_yaml_timestamp) + +SafeConstructor.add_constructor( + u'tag:yaml.org,2002:omap', + SafeConstructor.construct_yaml_omap) + +SafeConstructor.add_constructor( + u'tag:yaml.org,2002:pairs', + SafeConstructor.construct_yaml_pairs) + +SafeConstructor.add_constructor( + u'tag:yaml.org,2002:set', + SafeConstructor.construct_yaml_set) + +SafeConstructor.add_constructor( + u'tag:yaml.org,2002:str', + SafeConstructor.construct_yaml_str) + +SafeConstructor.add_constructor( + u'tag:yaml.org,2002:seq', + SafeConstructor.construct_yaml_seq) + +SafeConstructor.add_constructor( + u'tag:yaml.org,2002:map', + SafeConstructor.construct_yaml_map) + +SafeConstructor.add_constructor(None, + SafeConstructor.construct_undefined) + +class FullConstructor(SafeConstructor): + # 'extend' is blacklisted because it is used by + # construct_python_object_apply to add `listitems` to a newly generate + # python instance + def get_state_keys_blacklist(self): + return ['^extend$', '^__.*__$'] + + def get_state_keys_blacklist_regexp(self): + if not hasattr(self, 'state_keys_blacklist_regexp'): + self.state_keys_blacklist_regexp = re.compile('(' + '|'.join(self.get_state_keys_blacklist()) + ')') + return self.state_keys_blacklist_regexp + + def construct_python_str(self, node): + return self.construct_scalar(node).encode('utf-8') + + def construct_python_unicode(self, node): + return self.construct_scalar(node) + + def construct_python_long(self, node): + return long(self.construct_yaml_int(node)) + + def construct_python_complex(self, node): + return complex(self.construct_scalar(node)) + + def construct_python_tuple(self, node): + return tuple(self.construct_sequence(node)) + + def find_python_module(self, name, mark, unsafe=False): + if not name: + raise ConstructorError("while constructing a Python module", mark, + "expected non-empty name appended to the tag", mark) + if unsafe: + try: + __import__(name) + except ImportError, exc: + raise ConstructorError("while constructing a Python module", mark, + "cannot find module %r (%s)" % (name.encode('utf-8'), exc), mark) + if name not in sys.modules: + raise ConstructorError("while constructing a Python module", mark, + "module %r is not imported" % name.encode('utf-8'), mark) + return sys.modules[name] + + def find_python_name(self, name, mark, unsafe=False): + if not name: + raise ConstructorError("while constructing a Python object", mark, + "expected non-empty name appended to the tag", mark) + if u'.' in name: + module_name, object_name = name.rsplit('.', 1) + else: + module_name = '__builtin__' + object_name = name + if unsafe: + try: + __import__(module_name) + except ImportError, exc: + raise ConstructorError("while constructing a Python object", mark, + "cannot find module %r (%s)" % (module_name.encode('utf-8'), exc), mark) + if module_name not in sys.modules: + raise ConstructorError("while constructing a Python object", mark, + "module %r is not imported" % module_name.encode('utf-8'), mark) + module = sys.modules[module_name] + if not hasattr(module, object_name): + raise ConstructorError("while constructing a Python object", mark, + "cannot find %r in the module %r" % (object_name.encode('utf-8'), + module.__name__), mark) + return getattr(module, object_name) + + def construct_python_name(self, suffix, node): + value = self.construct_scalar(node) + if value: + raise ConstructorError("while constructing a Python name", node.start_mark, + "expected the empty value, but found %r" % value.encode('utf-8'), + node.start_mark) + return self.find_python_name(suffix, node.start_mark) + + def construct_python_module(self, suffix, node): + value = self.construct_scalar(node) + if value: + raise ConstructorError("while constructing a Python module", node.start_mark, + "expected the empty value, but found %r" % value.encode('utf-8'), + node.start_mark) + return self.find_python_module(suffix, node.start_mark) + + class classobj: pass + + def make_python_instance(self, suffix, node, + args=None, kwds=None, newobj=False, unsafe=False): + if not args: + args = [] + if not kwds: + kwds = {} + cls = self.find_python_name(suffix, node.start_mark) + if not (unsafe or isinstance(cls, type) or isinstance(cls, type(self.classobj))): + raise ConstructorError("while constructing a Python instance", node.start_mark, + "expected a class, but found %r" % type(cls), + node.start_mark) + if newobj and isinstance(cls, type(self.classobj)) \ + and not args and not kwds: + instance = self.classobj() + instance.__class__ = cls + return instance + elif newobj and isinstance(cls, type): + return cls.__new__(cls, *args, **kwds) + else: + return cls(*args, **kwds) + + def set_python_instance_state(self, instance, state, unsafe=False): + if hasattr(instance, '__setstate__'): + instance.__setstate__(state) + else: + slotstate = {} + if isinstance(state, tuple) and len(state) == 2: + state, slotstate = state + if hasattr(instance, '__dict__'): + if not unsafe and state: + for key in state.keys(): + self.check_state_key(key) + instance.__dict__.update(state) + elif state: + slotstate.update(state) + for key, value in slotstate.items(): + if not unsafe: + self.check_state_key(key) + setattr(instance, key, value) + + def construct_python_object(self, suffix, node): + # Format: + # !!python/object:module.name { ... state ... } + instance = self.make_python_instance(suffix, node, newobj=True) + yield instance + deep = hasattr(instance, '__setstate__') + state = self.construct_mapping(node, deep=deep) + self.set_python_instance_state(instance, state) + + def construct_python_object_apply(self, suffix, node, newobj=False): + # Format: + # !!python/object/apply # (or !!python/object/new) + # args: [ ... arguments ... ] + # kwds: { ... keywords ... } + # state: ... state ... + # listitems: [ ... listitems ... ] + # dictitems: { ... dictitems ... } + # or short format: + # !!python/object/apply [ ... arguments ... ] + # The difference between !!python/object/apply and !!python/object/new + # is how an object is created, check make_python_instance for details. + if isinstance(node, SequenceNode): + args = self.construct_sequence(node, deep=True) + kwds = {} + state = {} + listitems = [] + dictitems = {} + else: + value = self.construct_mapping(node, deep=True) + args = value.get('args', []) + kwds = value.get('kwds', {}) + state = value.get('state', {}) + listitems = value.get('listitems', []) + dictitems = value.get('dictitems', {}) + instance = self.make_python_instance(suffix, node, args, kwds, newobj) + if state: + self.set_python_instance_state(instance, state) + if listitems: + instance.extend(listitems) + if dictitems: + for key in dictitems: + instance[key] = dictitems[key] + return instance + + def construct_python_object_new(self, suffix, node): + return self.construct_python_object_apply(suffix, node, newobj=True) + +FullConstructor.add_constructor( + u'tag:yaml.org,2002:python/none', + FullConstructor.construct_yaml_null) + +FullConstructor.add_constructor( + u'tag:yaml.org,2002:python/bool', + FullConstructor.construct_yaml_bool) + +FullConstructor.add_constructor( + u'tag:yaml.org,2002:python/str', + FullConstructor.construct_python_str) + +FullConstructor.add_constructor( + u'tag:yaml.org,2002:python/unicode', + FullConstructor.construct_python_unicode) + +FullConstructor.add_constructor( + u'tag:yaml.org,2002:python/int', + FullConstructor.construct_yaml_int) + +FullConstructor.add_constructor( + u'tag:yaml.org,2002:python/long', + FullConstructor.construct_python_long) + +FullConstructor.add_constructor( + u'tag:yaml.org,2002:python/float', + FullConstructor.construct_yaml_float) + +FullConstructor.add_constructor( + u'tag:yaml.org,2002:python/complex', + FullConstructor.construct_python_complex) + +FullConstructor.add_constructor( + u'tag:yaml.org,2002:python/list', + FullConstructor.construct_yaml_seq) + +FullConstructor.add_constructor( + u'tag:yaml.org,2002:python/tuple', + FullConstructor.construct_python_tuple) + +FullConstructor.add_constructor( + u'tag:yaml.org,2002:python/dict', + FullConstructor.construct_yaml_map) + +FullConstructor.add_multi_constructor( + u'tag:yaml.org,2002:python/name:', + FullConstructor.construct_python_name) + +class UnsafeConstructor(FullConstructor): + + def find_python_module(self, name, mark): + return super(UnsafeConstructor, self).find_python_module(name, mark, unsafe=True) + + def find_python_name(self, name, mark): + return super(UnsafeConstructor, self).find_python_name(name, mark, unsafe=True) + + def make_python_instance(self, suffix, node, args=None, kwds=None, newobj=False): + return super(UnsafeConstructor, self).make_python_instance( + suffix, node, args, kwds, newobj, unsafe=True) + + def set_python_instance_state(self, instance, state): + return super(UnsafeConstructor, self).set_python_instance_state( + instance, state, unsafe=True) + +UnsafeConstructor.add_multi_constructor( + u'tag:yaml.org,2002:python/module:', + UnsafeConstructor.construct_python_module) + +UnsafeConstructor.add_multi_constructor( + u'tag:yaml.org,2002:python/object:', + UnsafeConstructor.construct_python_object) + +UnsafeConstructor.add_multi_constructor( + u'tag:yaml.org,2002:python/object/new:', + UnsafeConstructor.construct_python_object_new) + +UnsafeConstructor.add_multi_constructor( + u'tag:yaml.org,2002:python/object/apply:', + UnsafeConstructor.construct_python_object_apply) + +# Constructor is same as UnsafeConstructor. Need to leave this in place in case +# people have extended it directly. +class Constructor(UnsafeConstructor): + pass diff --git a/third_party/python/PyYAML/lib/yaml/cyaml.py b/third_party/python/PyYAML/lib/yaml/cyaml.py new file mode 100644 index 0000000000..768b49d6b9 --- /dev/null +++ b/third_party/python/PyYAML/lib/yaml/cyaml.py @@ -0,0 +1,101 @@ + +__all__ = [ + 'CBaseLoader', 'CSafeLoader', 'CFullLoader', 'CUnsafeLoader', 'CLoader', + 'CBaseDumper', 'CSafeDumper', 'CDumper' +] + +from yaml._yaml import CParser, CEmitter + +from constructor import * + +from serializer import * +from representer import * + +from resolver import * + +class CBaseLoader(CParser, BaseConstructor, BaseResolver): + + def __init__(self, stream): + CParser.__init__(self, stream) + BaseConstructor.__init__(self) + BaseResolver.__init__(self) + +class CSafeLoader(CParser, SafeConstructor, Resolver): + + def __init__(self, stream): + CParser.__init__(self, stream) + SafeConstructor.__init__(self) + Resolver.__init__(self) + +class CFullLoader(CParser, FullConstructor, Resolver): + + def __init__(self, stream): + CParser.__init__(self, stream) + FullConstructor.__init__(self) + Resolver.__init__(self) + +class CUnsafeLoader(CParser, UnsafeConstructor, Resolver): + + def __init__(self, stream): + CParser.__init__(self, stream) + UnsafeConstructor.__init__(self) + Resolver.__init__(self) + +class CLoader(CParser, Constructor, Resolver): + + def __init__(self, stream): + CParser.__init__(self, stream) + Constructor.__init__(self) + Resolver.__init__(self) + +class CBaseDumper(CEmitter, BaseRepresenter, BaseResolver): + + def __init__(self, stream, + default_style=None, default_flow_style=False, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None, sort_keys=True): + CEmitter.__init__(self, stream, canonical=canonical, + indent=indent, width=width, encoding=encoding, + allow_unicode=allow_unicode, line_break=line_break, + explicit_start=explicit_start, explicit_end=explicit_end, + version=version, tags=tags) + Representer.__init__(self, default_style=default_style, + default_flow_style=default_flow_style, sort_keys=sort_keys) + Resolver.__init__(self) + +class CSafeDumper(CEmitter, SafeRepresenter, Resolver): + + def __init__(self, stream, + default_style=None, default_flow_style=False, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None, sort_keys=True): + CEmitter.__init__(self, stream, canonical=canonical, + indent=indent, width=width, encoding=encoding, + allow_unicode=allow_unicode, line_break=line_break, + explicit_start=explicit_start, explicit_end=explicit_end, + version=version, tags=tags) + SafeRepresenter.__init__(self, default_style=default_style, + default_flow_style=default_flow_style, sort_keys=sort_keys) + Resolver.__init__(self) + +class CDumper(CEmitter, Serializer, Representer, Resolver): + + def __init__(self, stream, + default_style=None, default_flow_style=False, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None, sort_keys=True): + CEmitter.__init__(self, stream, canonical=canonical, + indent=indent, width=width, encoding=encoding, + allow_unicode=allow_unicode, line_break=line_break, + explicit_start=explicit_start, explicit_end=explicit_end, + version=version, tags=tags) + Representer.__init__(self, default_style=default_style, + default_flow_style=default_flow_style, sort_keys=sort_keys) + Resolver.__init__(self) + diff --git a/third_party/python/PyYAML/lib/yaml/dumper.py b/third_party/python/PyYAML/lib/yaml/dumper.py new file mode 100644 index 0000000000..f9cd49fda5 --- /dev/null +++ b/third_party/python/PyYAML/lib/yaml/dumper.py @@ -0,0 +1,62 @@ + +__all__ = ['BaseDumper', 'SafeDumper', 'Dumper'] + +from emitter import * +from serializer import * +from representer import * +from resolver import * + +class BaseDumper(Emitter, Serializer, BaseRepresenter, BaseResolver): + + def __init__(self, stream, + default_style=None, default_flow_style=False, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None, sort_keys=True): + Emitter.__init__(self, stream, canonical=canonical, + indent=indent, width=width, + allow_unicode=allow_unicode, line_break=line_break) + Serializer.__init__(self, encoding=encoding, + explicit_start=explicit_start, explicit_end=explicit_end, + version=version, tags=tags) + Representer.__init__(self, default_style=default_style, + default_flow_style=default_flow_style, sort_keys=sort_keys) + Resolver.__init__(self) + +class SafeDumper(Emitter, Serializer, SafeRepresenter, Resolver): + + def __init__(self, stream, + default_style=None, default_flow_style=False, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None, sort_keys=True): + Emitter.__init__(self, stream, canonical=canonical, + indent=indent, width=width, + allow_unicode=allow_unicode, line_break=line_break) + Serializer.__init__(self, encoding=encoding, + explicit_start=explicit_start, explicit_end=explicit_end, + version=version, tags=tags) + SafeRepresenter.__init__(self, default_style=default_style, + default_flow_style=default_flow_style, sort_keys=sort_keys) + Resolver.__init__(self) + +class Dumper(Emitter, Serializer, Representer, Resolver): + + def __init__(self, stream, + default_style=None, default_flow_style=False, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None, sort_keys=True): + Emitter.__init__(self, stream, canonical=canonical, + indent=indent, width=width, + allow_unicode=allow_unicode, line_break=line_break) + Serializer.__init__(self, encoding=encoding, + explicit_start=explicit_start, explicit_end=explicit_end, + version=version, tags=tags) + Representer.__init__(self, default_style=default_style, + default_flow_style=default_flow_style, sort_keys=sort_keys) + Resolver.__init__(self) + diff --git a/third_party/python/PyYAML/lib/yaml/emitter.py b/third_party/python/PyYAML/lib/yaml/emitter.py new file mode 100644 index 0000000000..23c25ca80a --- /dev/null +++ b/third_party/python/PyYAML/lib/yaml/emitter.py @@ -0,0 +1,1144 @@ + +# Emitter expects events obeying the following grammar: +# stream ::= STREAM-START document* STREAM-END +# document ::= DOCUMENT-START node DOCUMENT-END +# node ::= SCALAR | sequence | mapping +# sequence ::= SEQUENCE-START node* SEQUENCE-END +# mapping ::= MAPPING-START (node node)* MAPPING-END + +__all__ = ['Emitter', 'EmitterError'] + +import sys + +from error import YAMLError +from events import * + +has_ucs4 = sys.maxunicode > 0xffff + +class EmitterError(YAMLError): + pass + +class ScalarAnalysis(object): + def __init__(self, scalar, empty, multiline, + allow_flow_plain, allow_block_plain, + allow_single_quoted, allow_double_quoted, + allow_block): + self.scalar = scalar + self.empty = empty + self.multiline = multiline + self.allow_flow_plain = allow_flow_plain + self.allow_block_plain = allow_block_plain + self.allow_single_quoted = allow_single_quoted + self.allow_double_quoted = allow_double_quoted + self.allow_block = allow_block + +class Emitter(object): + + DEFAULT_TAG_PREFIXES = { + u'!' : u'!', + u'tag:yaml.org,2002:' : u'!!', + } + + def __init__(self, stream, canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None): + + # The stream should have the methods `write` and possibly `flush`. + self.stream = stream + + # Encoding can be overridden by STREAM-START. + self.encoding = None + + # Emitter is a state machine with a stack of states to handle nested + # structures. + self.states = [] + self.state = self.expect_stream_start + + # Current event and the event queue. + self.events = [] + self.event = None + + # The current indentation level and the stack of previous indents. + self.indents = [] + self.indent = None + + # Flow level. + self.flow_level = 0 + + # Contexts. + self.root_context = False + self.sequence_context = False + self.mapping_context = False + self.simple_key_context = False + + # Characteristics of the last emitted character: + # - current position. + # - is it a whitespace? + # - is it an indention character + # (indentation space, '-', '?', or ':')? + self.line = 0 + self.column = 0 + self.whitespace = True + self.indention = True + + # Whether the document requires an explicit document indicator + self.open_ended = False + + # Formatting details. + self.canonical = canonical + self.allow_unicode = allow_unicode + self.best_indent = 2 + if indent and 1 < indent < 10: + self.best_indent = indent + self.best_width = 80 + if width and width > self.best_indent*2: + self.best_width = width + self.best_line_break = u'\n' + if line_break in [u'\r', u'\n', u'\r\n']: + self.best_line_break = line_break + + # Tag prefixes. + self.tag_prefixes = None + + # Prepared anchor and tag. + self.prepared_anchor = None + self.prepared_tag = None + + # Scalar analysis and style. + self.analysis = None + self.style = None + + def dispose(self): + # Reset the state attributes (to clear self-references) + self.states = [] + self.state = None + + def emit(self, event): + self.events.append(event) + while not self.need_more_events(): + self.event = self.events.pop(0) + self.state() + self.event = None + + # In some cases, we wait for a few next events before emitting. + + def need_more_events(self): + if not self.events: + return True + event = self.events[0] + if isinstance(event, DocumentStartEvent): + return self.need_events(1) + elif isinstance(event, SequenceStartEvent): + return self.need_events(2) + elif isinstance(event, MappingStartEvent): + return self.need_events(3) + else: + return False + + def need_events(self, count): + level = 0 + for event in self.events[1:]: + if isinstance(event, (DocumentStartEvent, CollectionStartEvent)): + level += 1 + elif isinstance(event, (DocumentEndEvent, CollectionEndEvent)): + level -= 1 + elif isinstance(event, StreamEndEvent): + level = -1 + if level < 0: + return False + return (len(self.events) < count+1) + + def increase_indent(self, flow=False, indentless=False): + self.indents.append(self.indent) + if self.indent is None: + if flow: + self.indent = self.best_indent + else: + self.indent = 0 + elif not indentless: + self.indent += self.best_indent + + # States. + + # Stream handlers. + + def expect_stream_start(self): + if isinstance(self.event, StreamStartEvent): + if self.event.encoding and not getattr(self.stream, 'encoding', None): + self.encoding = self.event.encoding + self.write_stream_start() + self.state = self.expect_first_document_start + else: + raise EmitterError("expected StreamStartEvent, but got %s" + % self.event) + + def expect_nothing(self): + raise EmitterError("expected nothing, but got %s" % self.event) + + # Document handlers. + + def expect_first_document_start(self): + return self.expect_document_start(first=True) + + def expect_document_start(self, first=False): + if isinstance(self.event, DocumentStartEvent): + if (self.event.version or self.event.tags) and self.open_ended: + self.write_indicator(u'...', True) + self.write_indent() + if self.event.version: + version_text = self.prepare_version(self.event.version) + self.write_version_directive(version_text) + self.tag_prefixes = self.DEFAULT_TAG_PREFIXES.copy() + if self.event.tags: + handles = self.event.tags.keys() + handles.sort() + for handle in handles: + prefix = self.event.tags[handle] + self.tag_prefixes[prefix] = handle + handle_text = self.prepare_tag_handle(handle) + prefix_text = self.prepare_tag_prefix(prefix) + self.write_tag_directive(handle_text, prefix_text) + implicit = (first and not self.event.explicit and not self.canonical + and not self.event.version and not self.event.tags + and not self.check_empty_document()) + if not implicit: + self.write_indent() + self.write_indicator(u'---', True) + if self.canonical: + self.write_indent() + self.state = self.expect_document_root + elif isinstance(self.event, StreamEndEvent): + if self.open_ended: + self.write_indicator(u'...', True) + self.write_indent() + self.write_stream_end() + self.state = self.expect_nothing + else: + raise EmitterError("expected DocumentStartEvent, but got %s" + % self.event) + + def expect_document_end(self): + if isinstance(self.event, DocumentEndEvent): + self.write_indent() + if self.event.explicit: + self.write_indicator(u'...', True) + self.write_indent() + self.flush_stream() + self.state = self.expect_document_start + else: + raise EmitterError("expected DocumentEndEvent, but got %s" + % self.event) + + def expect_document_root(self): + self.states.append(self.expect_document_end) + self.expect_node(root=True) + + # Node handlers. + + def expect_node(self, root=False, sequence=False, mapping=False, + simple_key=False): + self.root_context = root + self.sequence_context = sequence + self.mapping_context = mapping + self.simple_key_context = simple_key + if isinstance(self.event, AliasEvent): + self.expect_alias() + elif isinstance(self.event, (ScalarEvent, CollectionStartEvent)): + self.process_anchor(u'&') + self.process_tag() + if isinstance(self.event, ScalarEvent): + self.expect_scalar() + elif isinstance(self.event, SequenceStartEvent): + if self.flow_level or self.canonical or self.event.flow_style \ + or self.check_empty_sequence(): + self.expect_flow_sequence() + else: + self.expect_block_sequence() + elif isinstance(self.event, MappingStartEvent): + if self.flow_level or self.canonical or self.event.flow_style \ + or self.check_empty_mapping(): + self.expect_flow_mapping() + else: + self.expect_block_mapping() + else: + raise EmitterError("expected NodeEvent, but got %s" % self.event) + + def expect_alias(self): + if self.event.anchor is None: + raise EmitterError("anchor is not specified for alias") + self.process_anchor(u'*') + self.state = self.states.pop() + + def expect_scalar(self): + self.increase_indent(flow=True) + self.process_scalar() + self.indent = self.indents.pop() + self.state = self.states.pop() + + # Flow sequence handlers. + + def expect_flow_sequence(self): + self.write_indicator(u'[', True, whitespace=True) + self.flow_level += 1 + self.increase_indent(flow=True) + self.state = self.expect_first_flow_sequence_item + + def expect_first_flow_sequence_item(self): + if isinstance(self.event, SequenceEndEvent): + self.indent = self.indents.pop() + self.flow_level -= 1 + self.write_indicator(u']', False) + self.state = self.states.pop() + else: + if self.canonical or self.column > self.best_width: + self.write_indent() + self.states.append(self.expect_flow_sequence_item) + self.expect_node(sequence=True) + + def expect_flow_sequence_item(self): + if isinstance(self.event, SequenceEndEvent): + self.indent = self.indents.pop() + self.flow_level -= 1 + if self.canonical: + self.write_indicator(u',', False) + self.write_indent() + self.write_indicator(u']', False) + self.state = self.states.pop() + else: + self.write_indicator(u',', False) + if self.canonical or self.column > self.best_width: + self.write_indent() + self.states.append(self.expect_flow_sequence_item) + self.expect_node(sequence=True) + + # Flow mapping handlers. + + def expect_flow_mapping(self): + self.write_indicator(u'{', True, whitespace=True) + self.flow_level += 1 + self.increase_indent(flow=True) + self.state = self.expect_first_flow_mapping_key + + def expect_first_flow_mapping_key(self): + if isinstance(self.event, MappingEndEvent): + self.indent = self.indents.pop() + self.flow_level -= 1 + self.write_indicator(u'}', False) + self.state = self.states.pop() + else: + if self.canonical or self.column > self.best_width: + self.write_indent() + if not self.canonical and self.check_simple_key(): + self.states.append(self.expect_flow_mapping_simple_value) + self.expect_node(mapping=True, simple_key=True) + else: + self.write_indicator(u'?', True) + self.states.append(self.expect_flow_mapping_value) + self.expect_node(mapping=True) + + def expect_flow_mapping_key(self): + if isinstance(self.event, MappingEndEvent): + self.indent = self.indents.pop() + self.flow_level -= 1 + if self.canonical: + self.write_indicator(u',', False) + self.write_indent() + self.write_indicator(u'}', False) + self.state = self.states.pop() + else: + self.write_indicator(u',', False) + if self.canonical or self.column > self.best_width: + self.write_indent() + if not self.canonical and self.check_simple_key(): + self.states.append(self.expect_flow_mapping_simple_value) + self.expect_node(mapping=True, simple_key=True) + else: + self.write_indicator(u'?', True) + self.states.append(self.expect_flow_mapping_value) + self.expect_node(mapping=True) + + def expect_flow_mapping_simple_value(self): + self.write_indicator(u':', False) + self.states.append(self.expect_flow_mapping_key) + self.expect_node(mapping=True) + + def expect_flow_mapping_value(self): + if self.canonical or self.column > self.best_width: + self.write_indent() + self.write_indicator(u':', True) + self.states.append(self.expect_flow_mapping_key) + self.expect_node(mapping=True) + + # Block sequence handlers. + + def expect_block_sequence(self): + indentless = (self.mapping_context and not self.indention) + self.increase_indent(flow=False, indentless=indentless) + self.state = self.expect_first_block_sequence_item + + def expect_first_block_sequence_item(self): + return self.expect_block_sequence_item(first=True) + + def expect_block_sequence_item(self, first=False): + if not first and isinstance(self.event, SequenceEndEvent): + self.indent = self.indents.pop() + self.state = self.states.pop() + else: + self.write_indent() + self.write_indicator(u'-', True, indention=True) + self.states.append(self.expect_block_sequence_item) + self.expect_node(sequence=True) + + # Block mapping handlers. + + def expect_block_mapping(self): + self.increase_indent(flow=False) + self.state = self.expect_first_block_mapping_key + + def expect_first_block_mapping_key(self): + return self.expect_block_mapping_key(first=True) + + def expect_block_mapping_key(self, first=False): + if not first and isinstance(self.event, MappingEndEvent): + self.indent = self.indents.pop() + self.state = self.states.pop() + else: + self.write_indent() + if self.check_simple_key(): + self.states.append(self.expect_block_mapping_simple_value) + self.expect_node(mapping=True, simple_key=True) + else: + self.write_indicator(u'?', True, indention=True) + self.states.append(self.expect_block_mapping_value) + self.expect_node(mapping=True) + + def expect_block_mapping_simple_value(self): + self.write_indicator(u':', False) + self.states.append(self.expect_block_mapping_key) + self.expect_node(mapping=True) + + def expect_block_mapping_value(self): + self.write_indent() + self.write_indicator(u':', True, indention=True) + self.states.append(self.expect_block_mapping_key) + self.expect_node(mapping=True) + + # Checkers. + + def check_empty_sequence(self): + return (isinstance(self.event, SequenceStartEvent) and self.events + and isinstance(self.events[0], SequenceEndEvent)) + + def check_empty_mapping(self): + return (isinstance(self.event, MappingStartEvent) and self.events + and isinstance(self.events[0], MappingEndEvent)) + + def check_empty_document(self): + if not isinstance(self.event, DocumentStartEvent) or not self.events: + return False + event = self.events[0] + return (isinstance(event, ScalarEvent) and event.anchor is None + and event.tag is None and event.implicit and event.value == u'') + + def check_simple_key(self): + length = 0 + if isinstance(self.event, NodeEvent) and self.event.anchor is not None: + if self.prepared_anchor is None: + self.prepared_anchor = self.prepare_anchor(self.event.anchor) + length += len(self.prepared_anchor) + if isinstance(self.event, (ScalarEvent, CollectionStartEvent)) \ + and self.event.tag is not None: + if self.prepared_tag is None: + self.prepared_tag = self.prepare_tag(self.event.tag) + length += len(self.prepared_tag) + if isinstance(self.event, ScalarEvent): + if self.analysis is None: + self.analysis = self.analyze_scalar(self.event.value) + length += len(self.analysis.scalar) + return (length < 128 and (isinstance(self.event, AliasEvent) + or (isinstance(self.event, ScalarEvent) + and not self.analysis.empty and not self.analysis.multiline) + or self.check_empty_sequence() or self.check_empty_mapping())) + + # Anchor, Tag, and Scalar processors. + + def process_anchor(self, indicator): + if self.event.anchor is None: + self.prepared_anchor = None + return + if self.prepared_anchor is None: + self.prepared_anchor = self.prepare_anchor(self.event.anchor) + if self.prepared_anchor: + self.write_indicator(indicator+self.prepared_anchor, True) + self.prepared_anchor = None + + def process_tag(self): + tag = self.event.tag + if isinstance(self.event, ScalarEvent): + if self.style is None: + self.style = self.choose_scalar_style() + if ((not self.canonical or tag is None) and + ((self.style == '' and self.event.implicit[0]) + or (self.style != '' and self.event.implicit[1]))): + self.prepared_tag = None + return + if self.event.implicit[0] and tag is None: + tag = u'!' + self.prepared_tag = None + else: + if (not self.canonical or tag is None) and self.event.implicit: + self.prepared_tag = None + return + if tag is None: + raise EmitterError("tag is not specified") + if self.prepared_tag is None: + self.prepared_tag = self.prepare_tag(tag) + if self.prepared_tag: + self.write_indicator(self.prepared_tag, True) + self.prepared_tag = None + + def choose_scalar_style(self): + if self.analysis is None: + self.analysis = self.analyze_scalar(self.event.value) + if self.event.style == '"' or self.canonical: + return '"' + if not self.event.style and self.event.implicit[0]: + if (not (self.simple_key_context and + (self.analysis.empty or self.analysis.multiline)) + and (self.flow_level and self.analysis.allow_flow_plain + or (not self.flow_level and self.analysis.allow_block_plain))): + return '' + if self.event.style and self.event.style in '|>': + if (not self.flow_level and not self.simple_key_context + and self.analysis.allow_block): + return self.event.style + if not self.event.style or self.event.style == '\'': + if (self.analysis.allow_single_quoted and + not (self.simple_key_context and self.analysis.multiline)): + return '\'' + return '"' + + def process_scalar(self): + if self.analysis is None: + self.analysis = self.analyze_scalar(self.event.value) + if self.style is None: + self.style = self.choose_scalar_style() + split = (not self.simple_key_context) + #if self.analysis.multiline and split \ + # and (not self.style or self.style in '\'\"'): + # self.write_indent() + if self.style == '"': + self.write_double_quoted(self.analysis.scalar, split) + elif self.style == '\'': + self.write_single_quoted(self.analysis.scalar, split) + elif self.style == '>': + self.write_folded(self.analysis.scalar) + elif self.style == '|': + self.write_literal(self.analysis.scalar) + else: + self.write_plain(self.analysis.scalar, split) + self.analysis = None + self.style = None + + # Analyzers. + + def prepare_version(self, version): + major, minor = version + if major != 1: + raise EmitterError("unsupported YAML version: %d.%d" % (major, minor)) + return u'%d.%d' % (major, minor) + + def prepare_tag_handle(self, handle): + if not handle: + raise EmitterError("tag handle must not be empty") + if handle[0] != u'!' or handle[-1] != u'!': + raise EmitterError("tag handle must start and end with '!': %r" + % (handle.encode('utf-8'))) + for ch in handle[1:-1]: + if not (u'0' <= ch <= u'9' or u'A' <= ch <= u'Z' or u'a' <= ch <= u'z' \ + or ch in u'-_'): + raise EmitterError("invalid character %r in the tag handle: %r" + % (ch.encode('utf-8'), handle.encode('utf-8'))) + return handle + + def prepare_tag_prefix(self, prefix): + if not prefix: + raise EmitterError("tag prefix must not be empty") + chunks = [] + start = end = 0 + if prefix[0] == u'!': + end = 1 + while end < len(prefix): + ch = prefix[end] + if u'0' <= ch <= u'9' or u'A' <= ch <= u'Z' or u'a' <= ch <= u'z' \ + or ch in u'-;/?!:@&=+$,_.~*\'()[]': + end += 1 + else: + if start < end: + chunks.append(prefix[start:end]) + start = end = end+1 + data = ch.encode('utf-8') + for ch in data: + chunks.append(u'%%%02X' % ord(ch)) + if start < end: + chunks.append(prefix[start:end]) + return u''.join(chunks) + + def prepare_tag(self, tag): + if not tag: + raise EmitterError("tag must not be empty") + if tag == u'!': + return tag + handle = None + suffix = tag + prefixes = self.tag_prefixes.keys() + prefixes.sort() + for prefix in prefixes: + if tag.startswith(prefix) \ + and (prefix == u'!' or len(prefix) < len(tag)): + handle = self.tag_prefixes[prefix] + suffix = tag[len(prefix):] + chunks = [] + start = end = 0 + while end < len(suffix): + ch = suffix[end] + if u'0' <= ch <= u'9' or u'A' <= ch <= u'Z' or u'a' <= ch <= u'z' \ + or ch in u'-;/?:@&=+$,_.~*\'()[]' \ + or (ch == u'!' and handle != u'!'): + end += 1 + else: + if start < end: + chunks.append(suffix[start:end]) + start = end = end+1 + data = ch.encode('utf-8') + for ch in data: + chunks.append(u'%%%02X' % ord(ch)) + if start < end: + chunks.append(suffix[start:end]) + suffix_text = u''.join(chunks) + if handle: + return u'%s%s' % (handle, suffix_text) + else: + return u'!<%s>' % suffix_text + + def prepare_anchor(self, anchor): + if not anchor: + raise EmitterError("anchor must not be empty") + for ch in anchor: + if not (u'0' <= ch <= u'9' or u'A' <= ch <= u'Z' or u'a' <= ch <= u'z' \ + or ch in u'-_'): + raise EmitterError("invalid character %r in the anchor: %r" + % (ch.encode('utf-8'), anchor.encode('utf-8'))) + return anchor + + def analyze_scalar(self, scalar): + + # Empty scalar is a special case. + if not scalar: + return ScalarAnalysis(scalar=scalar, empty=True, multiline=False, + allow_flow_plain=False, allow_block_plain=True, + allow_single_quoted=True, allow_double_quoted=True, + allow_block=False) + + # Indicators and special characters. + block_indicators = False + flow_indicators = False + line_breaks = False + special_characters = False + + # Important whitespace combinations. + leading_space = False + leading_break = False + trailing_space = False + trailing_break = False + break_space = False + space_break = False + + # Check document indicators. + if scalar.startswith(u'---') or scalar.startswith(u'...'): + block_indicators = True + flow_indicators = True + + # First character or preceded by a whitespace. + preceded_by_whitespace = True + + # Last character or followed by a whitespace. + followed_by_whitespace = (len(scalar) == 1 or + scalar[1] in u'\0 \t\r\n\x85\u2028\u2029') + + # The previous character is a space. + previous_space = False + + # The previous character is a break. + previous_break = False + + index = 0 + while index < len(scalar): + ch = scalar[index] + + # Check for indicators. + if index == 0: + # Leading indicators are special characters. + if ch in u'#,[]{}&*!|>\'\"%@`': + flow_indicators = True + block_indicators = True + if ch in u'?:': + flow_indicators = True + if followed_by_whitespace: + block_indicators = True + if ch == u'-' and followed_by_whitespace: + flow_indicators = True + block_indicators = True + else: + # Some indicators cannot appear within a scalar as well. + if ch in u',?[]{}': + flow_indicators = True + if ch == u':': + flow_indicators = True + if followed_by_whitespace: + block_indicators = True + if ch == u'#' and preceded_by_whitespace: + flow_indicators = True + block_indicators = True + + # Check for line breaks, special, and unicode characters. + if ch in u'\n\x85\u2028\u2029': + line_breaks = True + if not (ch == u'\n' or u'\x20' <= ch <= u'\x7E'): + if (ch == u'\x85' or u'\xA0' <= ch <= u'\uD7FF' + or u'\uE000' <= ch <= u'\uFFFD' + or (u'\U00010000' <= ch < u'\U0010ffff')) and ch != u'\uFEFF': + unicode_characters = True + if not self.allow_unicode: + special_characters = True + else: + special_characters = True + + # Detect important whitespace combinations. + if ch == u' ': + if index == 0: + leading_space = True + if index == len(scalar)-1: + trailing_space = True + if previous_break: + break_space = True + previous_space = True + previous_break = False + elif ch in u'\n\x85\u2028\u2029': + if index == 0: + leading_break = True + if index == len(scalar)-1: + trailing_break = True + if previous_space: + space_break = True + previous_space = False + previous_break = True + else: + previous_space = False + previous_break = False + + # Prepare for the next character. + index += 1 + preceded_by_whitespace = (ch in u'\0 \t\r\n\x85\u2028\u2029') + followed_by_whitespace = (index+1 >= len(scalar) or + scalar[index+1] in u'\0 \t\r\n\x85\u2028\u2029') + + # Let's decide what styles are allowed. + allow_flow_plain = True + allow_block_plain = True + allow_single_quoted = True + allow_double_quoted = True + allow_block = True + + # Leading and trailing whitespaces are bad for plain scalars. + if (leading_space or leading_break + or trailing_space or trailing_break): + allow_flow_plain = allow_block_plain = False + + # We do not permit trailing spaces for block scalars. + if trailing_space: + allow_block = False + + # Spaces at the beginning of a new line are only acceptable for block + # scalars. + if break_space: + allow_flow_plain = allow_block_plain = allow_single_quoted = False + + # Spaces followed by breaks, as well as special character are only + # allowed for double quoted scalars. + if space_break or special_characters: + allow_flow_plain = allow_block_plain = \ + allow_single_quoted = allow_block = False + + # Although the plain scalar writer supports breaks, we never emit + # multiline plain scalars. + if line_breaks: + allow_flow_plain = allow_block_plain = False + + # Flow indicators are forbidden for flow plain scalars. + if flow_indicators: + allow_flow_plain = False + + # Block indicators are forbidden for block plain scalars. + if block_indicators: + allow_block_plain = False + + return ScalarAnalysis(scalar=scalar, + empty=False, multiline=line_breaks, + allow_flow_plain=allow_flow_plain, + allow_block_plain=allow_block_plain, + allow_single_quoted=allow_single_quoted, + allow_double_quoted=allow_double_quoted, + allow_block=allow_block) + + # Writers. + + def flush_stream(self): + if hasattr(self.stream, 'flush'): + self.stream.flush() + + def write_stream_start(self): + # Write BOM if needed. + if self.encoding and self.encoding.startswith('utf-16'): + self.stream.write(u'\uFEFF'.encode(self.encoding)) + + def write_stream_end(self): + self.flush_stream() + + def write_indicator(self, indicator, need_whitespace, + whitespace=False, indention=False): + if self.whitespace or not need_whitespace: + data = indicator + else: + data = u' '+indicator + self.whitespace = whitespace + self.indention = self.indention and indention + self.column += len(data) + self.open_ended = False + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + + def write_indent(self): + indent = self.indent or 0 + if not self.indention or self.column > indent \ + or (self.column == indent and not self.whitespace): + self.write_line_break() + if self.column < indent: + self.whitespace = True + data = u' '*(indent-self.column) + self.column = indent + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + + def write_line_break(self, data=None): + if data is None: + data = self.best_line_break + self.whitespace = True + self.indention = True + self.line += 1 + self.column = 0 + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + + def write_version_directive(self, version_text): + data = u'%%YAML %s' % version_text + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + self.write_line_break() + + def write_tag_directive(self, handle_text, prefix_text): + data = u'%%TAG %s %s' % (handle_text, prefix_text) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + self.write_line_break() + + # Scalar streams. + + def write_single_quoted(self, text, split=True): + self.write_indicator(u'\'', True) + spaces = False + breaks = False + start = end = 0 + while end <= len(text): + ch = None + if end < len(text): + ch = text[end] + if spaces: + if ch is None or ch != u' ': + if start+1 == end and self.column > self.best_width and split \ + and start != 0 and end != len(text): + self.write_indent() + else: + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + elif breaks: + if ch is None or ch not in u'\n\x85\u2028\u2029': + if text[start] == u'\n': + self.write_line_break() + for br in text[start:end]: + if br == u'\n': + self.write_line_break() + else: + self.write_line_break(br) + self.write_indent() + start = end + else: + if ch is None or ch in u' \n\x85\u2028\u2029' or ch == u'\'': + if start < end: + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + if ch == u'\'': + data = u'\'\'' + self.column += 2 + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + 1 + if ch is not None: + spaces = (ch == u' ') + breaks = (ch in u'\n\x85\u2028\u2029') + end += 1 + self.write_indicator(u'\'', False) + + ESCAPE_REPLACEMENTS = { + u'\0': u'0', + u'\x07': u'a', + u'\x08': u'b', + u'\x09': u't', + u'\x0A': u'n', + u'\x0B': u'v', + u'\x0C': u'f', + u'\x0D': u'r', + u'\x1B': u'e', + u'\"': u'\"', + u'\\': u'\\', + u'\x85': u'N', + u'\xA0': u'_', + u'\u2028': u'L', + u'\u2029': u'P', + } + + def write_double_quoted(self, text, split=True): + self.write_indicator(u'"', True) + start = end = 0 + while end <= len(text): + ch = None + if end < len(text): + ch = text[end] + if ch is None or ch in u'"\\\x85\u2028\u2029\uFEFF' \ + or not (u'\x20' <= ch <= u'\x7E' + or (self.allow_unicode + and (u'\xA0' <= ch <= u'\uD7FF' + or u'\uE000' <= ch <= u'\uFFFD'))): + if start < end: + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + if ch is not None: + if ch in self.ESCAPE_REPLACEMENTS: + data = u'\\'+self.ESCAPE_REPLACEMENTS[ch] + elif ch <= u'\xFF': + data = u'\\x%02X' % ord(ch) + elif ch <= u'\uFFFF': + data = u'\\u%04X' % ord(ch) + else: + data = u'\\U%08X' % ord(ch) + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end+1 + if 0 < end < len(text)-1 and (ch == u' ' or start >= end) \ + and self.column+(end-start) > self.best_width and split: + data = text[start:end]+u'\\' + if start < end: + start = end + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + self.write_indent() + self.whitespace = False + self.indention = False + if text[start] == u' ': + data = u'\\' + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + end += 1 + self.write_indicator(u'"', False) + + def determine_block_hints(self, text): + hints = u'' + if text: + if text[0] in u' \n\x85\u2028\u2029': + hints += unicode(self.best_indent) + if text[-1] not in u'\n\x85\u2028\u2029': + hints += u'-' + elif len(text) == 1 or text[-2] in u'\n\x85\u2028\u2029': + hints += u'+' + return hints + + def write_folded(self, text): + hints = self.determine_block_hints(text) + self.write_indicator(u'>'+hints, True) + if hints[-1:] == u'+': + self.open_ended = True + self.write_line_break() + leading_space = True + spaces = False + breaks = True + start = end = 0 + while end <= len(text): + ch = None + if end < len(text): + ch = text[end] + if breaks: + if ch is None or ch not in u'\n\x85\u2028\u2029': + if not leading_space and ch is not None and ch != u' ' \ + and text[start] == u'\n': + self.write_line_break() + leading_space = (ch == u' ') + for br in text[start:end]: + if br == u'\n': + self.write_line_break() + else: + self.write_line_break(br) + if ch is not None: + self.write_indent() + start = end + elif spaces: + if ch != u' ': + if start+1 == end and self.column > self.best_width: + self.write_indent() + else: + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + else: + if ch is None or ch in u' \n\x85\u2028\u2029': + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + if ch is None: + self.write_line_break() + start = end + if ch is not None: + breaks = (ch in u'\n\x85\u2028\u2029') + spaces = (ch == u' ') + end += 1 + + def write_literal(self, text): + hints = self.determine_block_hints(text) + self.write_indicator(u'|'+hints, True) + if hints[-1:] == u'+': + self.open_ended = True + self.write_line_break() + breaks = True + start = end = 0 + while end <= len(text): + ch = None + if end < len(text): + ch = text[end] + if breaks: + if ch is None or ch not in u'\n\x85\u2028\u2029': + for br in text[start:end]: + if br == u'\n': + self.write_line_break() + else: + self.write_line_break(br) + if ch is not None: + self.write_indent() + start = end + else: + if ch is None or ch in u'\n\x85\u2028\u2029': + data = text[start:end] + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + if ch is None: + self.write_line_break() + start = end + if ch is not None: + breaks = (ch in u'\n\x85\u2028\u2029') + end += 1 + + def write_plain(self, text, split=True): + if self.root_context: + self.open_ended = True + if not text: + return + if not self.whitespace: + data = u' ' + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + self.whitespace = False + self.indention = False + spaces = False + breaks = False + start = end = 0 + while end <= len(text): + ch = None + if end < len(text): + ch = text[end] + if spaces: + if ch != u' ': + if start+1 == end and self.column > self.best_width and split: + self.write_indent() + self.whitespace = False + self.indention = False + else: + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + elif breaks: + if ch not in u'\n\x85\u2028\u2029': + if text[start] == u'\n': + self.write_line_break() + for br in text[start:end]: + if br == u'\n': + self.write_line_break() + else: + self.write_line_break(br) + self.write_indent() + self.whitespace = False + self.indention = False + start = end + else: + if ch is None or ch in u' \n\x85\u2028\u2029': + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + if ch is not None: + spaces = (ch == u' ') + breaks = (ch in u'\n\x85\u2028\u2029') + end += 1 diff --git a/third_party/python/PyYAML/lib/yaml/error.py b/third_party/python/PyYAML/lib/yaml/error.py new file mode 100644 index 0000000000..577686db5f --- /dev/null +++ b/third_party/python/PyYAML/lib/yaml/error.py @@ -0,0 +1,75 @@ + +__all__ = ['Mark', 'YAMLError', 'MarkedYAMLError'] + +class Mark(object): + + def __init__(self, name, index, line, column, buffer, pointer): + self.name = name + self.index = index + self.line = line + self.column = column + self.buffer = buffer + self.pointer = pointer + + def get_snippet(self, indent=4, max_length=75): + if self.buffer is None: + return None + head = '' + start = self.pointer + while start > 0 and self.buffer[start-1] not in u'\0\r\n\x85\u2028\u2029': + start -= 1 + if self.pointer-start > max_length/2-1: + head = ' ... ' + start += 5 + break + tail = '' + end = self.pointer + while end < len(self.buffer) and self.buffer[end] not in u'\0\r\n\x85\u2028\u2029': + end += 1 + if end-self.pointer > max_length/2-1: + tail = ' ... ' + end -= 5 + break + snippet = self.buffer[start:end].encode('utf-8') + return ' '*indent + head + snippet + tail + '\n' \ + + ' '*(indent+self.pointer-start+len(head)) + '^' + + def __str__(self): + snippet = self.get_snippet() + where = " in \"%s\", line %d, column %d" \ + % (self.name, self.line+1, self.column+1) + if snippet is not None: + where += ":\n"+snippet + return where + +class YAMLError(Exception): + pass + +class MarkedYAMLError(YAMLError): + + def __init__(self, context=None, context_mark=None, + problem=None, problem_mark=None, note=None): + self.context = context + self.context_mark = context_mark + self.problem = problem + self.problem_mark = problem_mark + self.note = note + + def __str__(self): + lines = [] + if self.context is not None: + lines.append(self.context) + if self.context_mark is not None \ + and (self.problem is None or self.problem_mark is None + or self.context_mark.name != self.problem_mark.name + or self.context_mark.line != self.problem_mark.line + or self.context_mark.column != self.problem_mark.column): + lines.append(str(self.context_mark)) + if self.problem is not None: + lines.append(self.problem) + if self.problem_mark is not None: + lines.append(str(self.problem_mark)) + if self.note is not None: + lines.append(self.note) + return '\n'.join(lines) + diff --git a/third_party/python/PyYAML/lib/yaml/events.py b/third_party/python/PyYAML/lib/yaml/events.py new file mode 100644 index 0000000000..f79ad389cb --- /dev/null +++ b/third_party/python/PyYAML/lib/yaml/events.py @@ -0,0 +1,86 @@ + +# Abstract classes. + +class Event(object): + def __init__(self, start_mark=None, end_mark=None): + self.start_mark = start_mark + self.end_mark = end_mark + def __repr__(self): + attributes = [key for key in ['anchor', 'tag', 'implicit', 'value'] + if hasattr(self, key)] + arguments = ', '.join(['%s=%r' % (key, getattr(self, key)) + for key in attributes]) + return '%s(%s)' % (self.__class__.__name__, arguments) + +class NodeEvent(Event): + def __init__(self, anchor, start_mark=None, end_mark=None): + self.anchor = anchor + self.start_mark = start_mark + self.end_mark = end_mark + +class CollectionStartEvent(NodeEvent): + def __init__(self, anchor, tag, implicit, start_mark=None, end_mark=None, + flow_style=None): + self.anchor = anchor + self.tag = tag + self.implicit = implicit + self.start_mark = start_mark + self.end_mark = end_mark + self.flow_style = flow_style + +class CollectionEndEvent(Event): + pass + +# Implementations. + +class StreamStartEvent(Event): + def __init__(self, start_mark=None, end_mark=None, encoding=None): + self.start_mark = start_mark + self.end_mark = end_mark + self.encoding = encoding + +class StreamEndEvent(Event): + pass + +class DocumentStartEvent(Event): + def __init__(self, start_mark=None, end_mark=None, + explicit=None, version=None, tags=None): + self.start_mark = start_mark + self.end_mark = end_mark + self.explicit = explicit + self.version = version + self.tags = tags + +class DocumentEndEvent(Event): + def __init__(self, start_mark=None, end_mark=None, + explicit=None): + self.start_mark = start_mark + self.end_mark = end_mark + self.explicit = explicit + +class AliasEvent(NodeEvent): + pass + +class ScalarEvent(NodeEvent): + def __init__(self, anchor, tag, implicit, value, + start_mark=None, end_mark=None, style=None): + self.anchor = anchor + self.tag = tag + self.implicit = implicit + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + self.style = style + +class SequenceStartEvent(CollectionStartEvent): + pass + +class SequenceEndEvent(CollectionEndEvent): + pass + +class MappingStartEvent(CollectionStartEvent): + pass + +class MappingEndEvent(CollectionEndEvent): + pass + diff --git a/third_party/python/PyYAML/lib/yaml/loader.py b/third_party/python/PyYAML/lib/yaml/loader.py new file mode 100644 index 0000000000..4d773c3cc1 --- /dev/null +++ b/third_party/python/PyYAML/lib/yaml/loader.py @@ -0,0 +1,63 @@ + +__all__ = ['BaseLoader', 'FullLoader', 'SafeLoader', 'Loader', 'UnsafeLoader'] + +from reader import * +from scanner import * +from parser import * +from composer import * +from constructor import * +from resolver import * + +class BaseLoader(Reader, Scanner, Parser, Composer, BaseConstructor, BaseResolver): + + def __init__(self, stream): + Reader.__init__(self, stream) + Scanner.__init__(self) + Parser.__init__(self) + Composer.__init__(self) + BaseConstructor.__init__(self) + BaseResolver.__init__(self) + +class FullLoader(Reader, Scanner, Parser, Composer, FullConstructor, Resolver): + + def __init__(self, stream): + Reader.__init__(self, stream) + Scanner.__init__(self) + Parser.__init__(self) + Composer.__init__(self) + FullConstructor.__init__(self) + Resolver.__init__(self) + +class SafeLoader(Reader, Scanner, Parser, Composer, SafeConstructor, Resolver): + + def __init__(self, stream): + Reader.__init__(self, stream) + Scanner.__init__(self) + Parser.__init__(self) + Composer.__init__(self) + SafeConstructor.__init__(self) + Resolver.__init__(self) + +class Loader(Reader, Scanner, Parser, Composer, Constructor, Resolver): + + def __init__(self, stream): + Reader.__init__(self, stream) + Scanner.__init__(self) + Parser.__init__(self) + Composer.__init__(self) + Constructor.__init__(self) + Resolver.__init__(self) + +# UnsafeLoader is the same as Loader (which is and was always unsafe on +# untrusted input). Use of either Loader or UnsafeLoader should be rare, since +# FullLoad should be able to load almost all YAML safely. Loader is left intact +# to ensure backwards compatibility. +class UnsafeLoader(Reader, Scanner, Parser, Composer, Constructor, Resolver): + + def __init__(self, stream): + Reader.__init__(self, stream) + Scanner.__init__(self) + Parser.__init__(self) + Composer.__init__(self) + Constructor.__init__(self) + Resolver.__init__(self) diff --git a/third_party/python/PyYAML/lib/yaml/nodes.py b/third_party/python/PyYAML/lib/yaml/nodes.py new file mode 100644 index 0000000000..c4f070c41e --- /dev/null +++ b/third_party/python/PyYAML/lib/yaml/nodes.py @@ -0,0 +1,49 @@ + +class Node(object): + def __init__(self, tag, value, start_mark, end_mark): + self.tag = tag + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + def __repr__(self): + value = self.value + #if isinstance(value, list): + # if len(value) == 0: + # value = '' + # elif len(value) == 1: + # value = '<1 item>' + # else: + # value = '<%d items>' % len(value) + #else: + # if len(value) > 75: + # value = repr(value[:70]+u' ... ') + # else: + # value = repr(value) + value = repr(value) + return '%s(tag=%r, value=%s)' % (self.__class__.__name__, self.tag, value) + +class ScalarNode(Node): + id = 'scalar' + def __init__(self, tag, value, + start_mark=None, end_mark=None, style=None): + self.tag = tag + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + self.style = style + +class CollectionNode(Node): + def __init__(self, tag, value, + start_mark=None, end_mark=None, flow_style=None): + self.tag = tag + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + self.flow_style = flow_style + +class SequenceNode(CollectionNode): + id = 'sequence' + +class MappingNode(CollectionNode): + id = 'mapping' + diff --git a/third_party/python/PyYAML/lib/yaml/parser.py b/third_party/python/PyYAML/lib/yaml/parser.py new file mode 100644 index 0000000000..f9e3057f33 --- /dev/null +++ b/third_party/python/PyYAML/lib/yaml/parser.py @@ -0,0 +1,589 @@ + +# The following YAML grammar is LL(1) and is parsed by a recursive descent +# parser. +# +# stream ::= STREAM-START implicit_document? explicit_document* STREAM-END +# implicit_document ::= block_node DOCUMENT-END* +# explicit_document ::= DIRECTIVE* DOCUMENT-START block_node? DOCUMENT-END* +# block_node_or_indentless_sequence ::= +# ALIAS +# | properties (block_content | indentless_block_sequence)? +# | block_content +# | indentless_block_sequence +# block_node ::= ALIAS +# | properties block_content? +# | block_content +# flow_node ::= ALIAS +# | properties flow_content? +# | flow_content +# properties ::= TAG ANCHOR? | ANCHOR TAG? +# block_content ::= block_collection | flow_collection | SCALAR +# flow_content ::= flow_collection | SCALAR +# block_collection ::= block_sequence | block_mapping +# flow_collection ::= flow_sequence | flow_mapping +# block_sequence ::= BLOCK-SEQUENCE-START (BLOCK-ENTRY block_node?)* BLOCK-END +# indentless_sequence ::= (BLOCK-ENTRY block_node?)+ +# block_mapping ::= BLOCK-MAPPING_START +# ((KEY block_node_or_indentless_sequence?)? +# (VALUE block_node_or_indentless_sequence?)?)* +# BLOCK-END +# flow_sequence ::= FLOW-SEQUENCE-START +# (flow_sequence_entry FLOW-ENTRY)* +# flow_sequence_entry? +# FLOW-SEQUENCE-END +# flow_sequence_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? +# flow_mapping ::= FLOW-MAPPING-START +# (flow_mapping_entry FLOW-ENTRY)* +# flow_mapping_entry? +# FLOW-MAPPING-END +# flow_mapping_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? +# +# FIRST sets: +# +# stream: { STREAM-START } +# explicit_document: { DIRECTIVE DOCUMENT-START } +# implicit_document: FIRST(block_node) +# block_node: { ALIAS TAG ANCHOR SCALAR BLOCK-SEQUENCE-START BLOCK-MAPPING-START FLOW-SEQUENCE-START FLOW-MAPPING-START } +# flow_node: { ALIAS ANCHOR TAG SCALAR FLOW-SEQUENCE-START FLOW-MAPPING-START } +# block_content: { BLOCK-SEQUENCE-START BLOCK-MAPPING-START FLOW-SEQUENCE-START FLOW-MAPPING-START SCALAR } +# flow_content: { FLOW-SEQUENCE-START FLOW-MAPPING-START SCALAR } +# block_collection: { BLOCK-SEQUENCE-START BLOCK-MAPPING-START } +# flow_collection: { FLOW-SEQUENCE-START FLOW-MAPPING-START } +# block_sequence: { BLOCK-SEQUENCE-START } +# block_mapping: { BLOCK-MAPPING-START } +# block_node_or_indentless_sequence: { ALIAS ANCHOR TAG SCALAR BLOCK-SEQUENCE-START BLOCK-MAPPING-START FLOW-SEQUENCE-START FLOW-MAPPING-START BLOCK-ENTRY } +# indentless_sequence: { ENTRY } +# flow_collection: { FLOW-SEQUENCE-START FLOW-MAPPING-START } +# flow_sequence: { FLOW-SEQUENCE-START } +# flow_mapping: { FLOW-MAPPING-START } +# flow_sequence_entry: { ALIAS ANCHOR TAG SCALAR FLOW-SEQUENCE-START FLOW-MAPPING-START KEY } +# flow_mapping_entry: { ALIAS ANCHOR TAG SCALAR FLOW-SEQUENCE-START FLOW-MAPPING-START KEY } + +__all__ = ['Parser', 'ParserError'] + +from error import MarkedYAMLError +from tokens import * +from events import * +from scanner import * + +class ParserError(MarkedYAMLError): + pass + +class Parser(object): + # Since writing a recursive-descendant parser is a straightforward task, we + # do not give many comments here. + + DEFAULT_TAGS = { + u'!': u'!', + u'!!': u'tag:yaml.org,2002:', + } + + def __init__(self): + self.current_event = None + self.yaml_version = None + self.tag_handles = {} + self.states = [] + self.marks = [] + self.state = self.parse_stream_start + + def dispose(self): + # Reset the state attributes (to clear self-references) + self.states = [] + self.state = None + + def check_event(self, *choices): + # Check the type of the next event. + if self.current_event is None: + if self.state: + self.current_event = self.state() + if self.current_event is not None: + if not choices: + return True + for choice in choices: + if isinstance(self.current_event, choice): + return True + return False + + def peek_event(self): + # Get the next event. + if self.current_event is None: + if self.state: + self.current_event = self.state() + return self.current_event + + def get_event(self): + # Get the next event and proceed further. + if self.current_event is None: + if self.state: + self.current_event = self.state() + value = self.current_event + self.current_event = None + return value + + # stream ::= STREAM-START implicit_document? explicit_document* STREAM-END + # implicit_document ::= block_node DOCUMENT-END* + # explicit_document ::= DIRECTIVE* DOCUMENT-START block_node? DOCUMENT-END* + + def parse_stream_start(self): + + # Parse the stream start. + token = self.get_token() + event = StreamStartEvent(token.start_mark, token.end_mark, + encoding=token.encoding) + + # Prepare the next state. + self.state = self.parse_implicit_document_start + + return event + + def parse_implicit_document_start(self): + + # Parse an implicit document. + if not self.check_token(DirectiveToken, DocumentStartToken, + StreamEndToken): + self.tag_handles = self.DEFAULT_TAGS + token = self.peek_token() + start_mark = end_mark = token.start_mark + event = DocumentStartEvent(start_mark, end_mark, + explicit=False) + + # Prepare the next state. + self.states.append(self.parse_document_end) + self.state = self.parse_block_node + + return event + + else: + return self.parse_document_start() + + def parse_document_start(self): + + # Parse any extra document end indicators. + while self.check_token(DocumentEndToken): + self.get_token() + + # Parse an explicit document. + if not self.check_token(StreamEndToken): + token = self.peek_token() + start_mark = token.start_mark + version, tags = self.process_directives() + if not self.check_token(DocumentStartToken): + raise ParserError(None, None, + "expected '', but found %r" + % self.peek_token().id, + self.peek_token().start_mark) + token = self.get_token() + end_mark = token.end_mark + event = DocumentStartEvent(start_mark, end_mark, + explicit=True, version=version, tags=tags) + self.states.append(self.parse_document_end) + self.state = self.parse_document_content + else: + # Parse the end of the stream. + token = self.get_token() + event = StreamEndEvent(token.start_mark, token.end_mark) + assert not self.states + assert not self.marks + self.state = None + return event + + def parse_document_end(self): + + # Parse the document end. + token = self.peek_token() + start_mark = end_mark = token.start_mark + explicit = False + if self.check_token(DocumentEndToken): + token = self.get_token() + end_mark = token.end_mark + explicit = True + event = DocumentEndEvent(start_mark, end_mark, + explicit=explicit) + + # Prepare the next state. + self.state = self.parse_document_start + + return event + + def parse_document_content(self): + if self.check_token(DirectiveToken, + DocumentStartToken, DocumentEndToken, StreamEndToken): + event = self.process_empty_scalar(self.peek_token().start_mark) + self.state = self.states.pop() + return event + else: + return self.parse_block_node() + + def process_directives(self): + self.yaml_version = None + self.tag_handles = {} + while self.check_token(DirectiveToken): + token = self.get_token() + if token.name == u'YAML': + if self.yaml_version is not None: + raise ParserError(None, None, + "found duplicate YAML directive", token.start_mark) + major, minor = token.value + if major != 1: + raise ParserError(None, None, + "found incompatible YAML document (version 1.* is required)", + token.start_mark) + self.yaml_version = token.value + elif token.name == u'TAG': + handle, prefix = token.value + if handle in self.tag_handles: + raise ParserError(None, None, + "duplicate tag handle %r" % handle.encode('utf-8'), + token.start_mark) + self.tag_handles[handle] = prefix + if self.tag_handles: + value = self.yaml_version, self.tag_handles.copy() + else: + value = self.yaml_version, None + for key in self.DEFAULT_TAGS: + if key not in self.tag_handles: + self.tag_handles[key] = self.DEFAULT_TAGS[key] + return value + + # block_node_or_indentless_sequence ::= ALIAS + # | properties (block_content | indentless_block_sequence)? + # | block_content + # | indentless_block_sequence + # block_node ::= ALIAS + # | properties block_content? + # | block_content + # flow_node ::= ALIAS + # | properties flow_content? + # | flow_content + # properties ::= TAG ANCHOR? | ANCHOR TAG? + # block_content ::= block_collection | flow_collection | SCALAR + # flow_content ::= flow_collection | SCALAR + # block_collection ::= block_sequence | block_mapping + # flow_collection ::= flow_sequence | flow_mapping + + def parse_block_node(self): + return self.parse_node(block=True) + + def parse_flow_node(self): + return self.parse_node() + + def parse_block_node_or_indentless_sequence(self): + return self.parse_node(block=True, indentless_sequence=True) + + def parse_node(self, block=False, indentless_sequence=False): + if self.check_token(AliasToken): + token = self.get_token() + event = AliasEvent(token.value, token.start_mark, token.end_mark) + self.state = self.states.pop() + else: + anchor = None + tag = None + start_mark = end_mark = tag_mark = None + if self.check_token(AnchorToken): + token = self.get_token() + start_mark = token.start_mark + end_mark = token.end_mark + anchor = token.value + if self.check_token(TagToken): + token = self.get_token() + tag_mark = token.start_mark + end_mark = token.end_mark + tag = token.value + elif self.check_token(TagToken): + token = self.get_token() + start_mark = tag_mark = token.start_mark + end_mark = token.end_mark + tag = token.value + if self.check_token(AnchorToken): + token = self.get_token() + end_mark = token.end_mark + anchor = token.value + if tag is not None: + handle, suffix = tag + if handle is not None: + if handle not in self.tag_handles: + raise ParserError("while parsing a node", start_mark, + "found undefined tag handle %r" % handle.encode('utf-8'), + tag_mark) + tag = self.tag_handles[handle]+suffix + else: + tag = suffix + #if tag == u'!': + # raise ParserError("while parsing a node", start_mark, + # "found non-specific tag '!'", tag_mark, + # "Please check 'http://pyyaml.org/wiki/YAMLNonSpecificTag' and share your opinion.") + if start_mark is None: + start_mark = end_mark = self.peek_token().start_mark + event = None + implicit = (tag is None or tag == u'!') + if indentless_sequence and self.check_token(BlockEntryToken): + end_mark = self.peek_token().end_mark + event = SequenceStartEvent(anchor, tag, implicit, + start_mark, end_mark) + self.state = self.parse_indentless_sequence_entry + else: + if self.check_token(ScalarToken): + token = self.get_token() + end_mark = token.end_mark + if (token.plain and tag is None) or tag == u'!': + implicit = (True, False) + elif tag is None: + implicit = (False, True) + else: + implicit = (False, False) + event = ScalarEvent(anchor, tag, implicit, token.value, + start_mark, end_mark, style=token.style) + self.state = self.states.pop() + elif self.check_token(FlowSequenceStartToken): + end_mark = self.peek_token().end_mark + event = SequenceStartEvent(anchor, tag, implicit, + start_mark, end_mark, flow_style=True) + self.state = self.parse_flow_sequence_first_entry + elif self.check_token(FlowMappingStartToken): + end_mark = self.peek_token().end_mark + event = MappingStartEvent(anchor, tag, implicit, + start_mark, end_mark, flow_style=True) + self.state = self.parse_flow_mapping_first_key + elif block and self.check_token(BlockSequenceStartToken): + end_mark = self.peek_token().start_mark + event = SequenceStartEvent(anchor, tag, implicit, + start_mark, end_mark, flow_style=False) + self.state = self.parse_block_sequence_first_entry + elif block and self.check_token(BlockMappingStartToken): + end_mark = self.peek_token().start_mark + event = MappingStartEvent(anchor, tag, implicit, + start_mark, end_mark, flow_style=False) + self.state = self.parse_block_mapping_first_key + elif anchor is not None or tag is not None: + # Empty scalars are allowed even if a tag or an anchor is + # specified. + event = ScalarEvent(anchor, tag, (implicit, False), u'', + start_mark, end_mark) + self.state = self.states.pop() + else: + if block: + node = 'block' + else: + node = 'flow' + token = self.peek_token() + raise ParserError("while parsing a %s node" % node, start_mark, + "expected the node content, but found %r" % token.id, + token.start_mark) + return event + + # block_sequence ::= BLOCK-SEQUENCE-START (BLOCK-ENTRY block_node?)* BLOCK-END + + def parse_block_sequence_first_entry(self): + token = self.get_token() + self.marks.append(token.start_mark) + return self.parse_block_sequence_entry() + + def parse_block_sequence_entry(self): + if self.check_token(BlockEntryToken): + token = self.get_token() + if not self.check_token(BlockEntryToken, BlockEndToken): + self.states.append(self.parse_block_sequence_entry) + return self.parse_block_node() + else: + self.state = self.parse_block_sequence_entry + return self.process_empty_scalar(token.end_mark) + if not self.check_token(BlockEndToken): + token = self.peek_token() + raise ParserError("while parsing a block collection", self.marks[-1], + "expected , but found %r" % token.id, token.start_mark) + token = self.get_token() + event = SequenceEndEvent(token.start_mark, token.end_mark) + self.state = self.states.pop() + self.marks.pop() + return event + + # indentless_sequence ::= (BLOCK-ENTRY block_node?)+ + + def parse_indentless_sequence_entry(self): + if self.check_token(BlockEntryToken): + token = self.get_token() + if not self.check_token(BlockEntryToken, + KeyToken, ValueToken, BlockEndToken): + self.states.append(self.parse_indentless_sequence_entry) + return self.parse_block_node() + else: + self.state = self.parse_indentless_sequence_entry + return self.process_empty_scalar(token.end_mark) + token = self.peek_token() + event = SequenceEndEvent(token.start_mark, token.start_mark) + self.state = self.states.pop() + return event + + # block_mapping ::= BLOCK-MAPPING_START + # ((KEY block_node_or_indentless_sequence?)? + # (VALUE block_node_or_indentless_sequence?)?)* + # BLOCK-END + + def parse_block_mapping_first_key(self): + token = self.get_token() + self.marks.append(token.start_mark) + return self.parse_block_mapping_key() + + def parse_block_mapping_key(self): + if self.check_token(KeyToken): + token = self.get_token() + if not self.check_token(KeyToken, ValueToken, BlockEndToken): + self.states.append(self.parse_block_mapping_value) + return self.parse_block_node_or_indentless_sequence() + else: + self.state = self.parse_block_mapping_value + return self.process_empty_scalar(token.end_mark) + if not self.check_token(BlockEndToken): + token = self.peek_token() + raise ParserError("while parsing a block mapping", self.marks[-1], + "expected , but found %r" % token.id, token.start_mark) + token = self.get_token() + event = MappingEndEvent(token.start_mark, token.end_mark) + self.state = self.states.pop() + self.marks.pop() + return event + + def parse_block_mapping_value(self): + if self.check_token(ValueToken): + token = self.get_token() + if not self.check_token(KeyToken, ValueToken, BlockEndToken): + self.states.append(self.parse_block_mapping_key) + return self.parse_block_node_or_indentless_sequence() + else: + self.state = self.parse_block_mapping_key + return self.process_empty_scalar(token.end_mark) + else: + self.state = self.parse_block_mapping_key + token = self.peek_token() + return self.process_empty_scalar(token.start_mark) + + # flow_sequence ::= FLOW-SEQUENCE-START + # (flow_sequence_entry FLOW-ENTRY)* + # flow_sequence_entry? + # FLOW-SEQUENCE-END + # flow_sequence_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? + # + # Note that while production rules for both flow_sequence_entry and + # flow_mapping_entry are equal, their interpretations are different. + # For `flow_sequence_entry`, the part `KEY flow_node? (VALUE flow_node?)?` + # generate an inline mapping (set syntax). + + def parse_flow_sequence_first_entry(self): + token = self.get_token() + self.marks.append(token.start_mark) + return self.parse_flow_sequence_entry(first=True) + + def parse_flow_sequence_entry(self, first=False): + if not self.check_token(FlowSequenceEndToken): + if not first: + if self.check_token(FlowEntryToken): + self.get_token() + else: + token = self.peek_token() + raise ParserError("while parsing a flow sequence", self.marks[-1], + "expected ',' or ']', but got %r" % token.id, token.start_mark) + + if self.check_token(KeyToken): + token = self.peek_token() + event = MappingStartEvent(None, None, True, + token.start_mark, token.end_mark, + flow_style=True) + self.state = self.parse_flow_sequence_entry_mapping_key + return event + elif not self.check_token(FlowSequenceEndToken): + self.states.append(self.parse_flow_sequence_entry) + return self.parse_flow_node() + token = self.get_token() + event = SequenceEndEvent(token.start_mark, token.end_mark) + self.state = self.states.pop() + self.marks.pop() + return event + + def parse_flow_sequence_entry_mapping_key(self): + token = self.get_token() + if not self.check_token(ValueToken, + FlowEntryToken, FlowSequenceEndToken): + self.states.append(self.parse_flow_sequence_entry_mapping_value) + return self.parse_flow_node() + else: + self.state = self.parse_flow_sequence_entry_mapping_value + return self.process_empty_scalar(token.end_mark) + + def parse_flow_sequence_entry_mapping_value(self): + if self.check_token(ValueToken): + token = self.get_token() + if not self.check_token(FlowEntryToken, FlowSequenceEndToken): + self.states.append(self.parse_flow_sequence_entry_mapping_end) + return self.parse_flow_node() + else: + self.state = self.parse_flow_sequence_entry_mapping_end + return self.process_empty_scalar(token.end_mark) + else: + self.state = self.parse_flow_sequence_entry_mapping_end + token = self.peek_token() + return self.process_empty_scalar(token.start_mark) + + def parse_flow_sequence_entry_mapping_end(self): + self.state = self.parse_flow_sequence_entry + token = self.peek_token() + return MappingEndEvent(token.start_mark, token.start_mark) + + # flow_mapping ::= FLOW-MAPPING-START + # (flow_mapping_entry FLOW-ENTRY)* + # flow_mapping_entry? + # FLOW-MAPPING-END + # flow_mapping_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? + + def parse_flow_mapping_first_key(self): + token = self.get_token() + self.marks.append(token.start_mark) + return self.parse_flow_mapping_key(first=True) + + def parse_flow_mapping_key(self, first=False): + if not self.check_token(FlowMappingEndToken): + if not first: + if self.check_token(FlowEntryToken): + self.get_token() + else: + token = self.peek_token() + raise ParserError("while parsing a flow mapping", self.marks[-1], + "expected ',' or '}', but got %r" % token.id, token.start_mark) + if self.check_token(KeyToken): + token = self.get_token() + if not self.check_token(ValueToken, + FlowEntryToken, FlowMappingEndToken): + self.states.append(self.parse_flow_mapping_value) + return self.parse_flow_node() + else: + self.state = self.parse_flow_mapping_value + return self.process_empty_scalar(token.end_mark) + elif not self.check_token(FlowMappingEndToken): + self.states.append(self.parse_flow_mapping_empty_value) + return self.parse_flow_node() + token = self.get_token() + event = MappingEndEvent(token.start_mark, token.end_mark) + self.state = self.states.pop() + self.marks.pop() + return event + + def parse_flow_mapping_value(self): + if self.check_token(ValueToken): + token = self.get_token() + if not self.check_token(FlowEntryToken, FlowMappingEndToken): + self.states.append(self.parse_flow_mapping_key) + return self.parse_flow_node() + else: + self.state = self.parse_flow_mapping_key + return self.process_empty_scalar(token.end_mark) + else: + self.state = self.parse_flow_mapping_key + token = self.peek_token() + return self.process_empty_scalar(token.start_mark) + + def parse_flow_mapping_empty_value(self): + self.state = self.parse_flow_mapping_key + return self.process_empty_scalar(self.peek_token().start_mark) + + def process_empty_scalar(self, mark): + return ScalarEvent(None, None, (True, False), u'', mark, mark) + diff --git a/third_party/python/PyYAML/lib/yaml/reader.py b/third_party/python/PyYAML/lib/yaml/reader.py new file mode 100644 index 0000000000..4c42150989 --- /dev/null +++ b/third_party/python/PyYAML/lib/yaml/reader.py @@ -0,0 +1,193 @@ +# This module contains abstractions for the input stream. You don't have to +# looks further, there are no pretty code. +# +# We define two classes here. +# +# Mark(source, line, column) +# It's just a record and its only use is producing nice error messages. +# Parser does not use it for any other purposes. +# +# Reader(source, data) +# Reader determines the encoding of `data` and converts it to unicode. +# Reader provides the following methods and attributes: +# reader.peek(length=1) - return the next `length` characters +# reader.forward(length=1) - move the current position to `length` characters. +# reader.index - the number of the current character. +# reader.line, stream.column - the line and the column of the current character. + +__all__ = ['Reader', 'ReaderError'] + +from error import YAMLError, Mark + +import codecs, re, sys + +has_ucs4 = sys.maxunicode > 0xffff + +class ReaderError(YAMLError): + + def __init__(self, name, position, character, encoding, reason): + self.name = name + self.character = character + self.position = position + self.encoding = encoding + self.reason = reason + + def __str__(self): + if isinstance(self.character, str): + return "'%s' codec can't decode byte #x%02x: %s\n" \ + " in \"%s\", position %d" \ + % (self.encoding, ord(self.character), self.reason, + self.name, self.position) + else: + return "unacceptable character #x%04x: %s\n" \ + " in \"%s\", position %d" \ + % (self.character, self.reason, + self.name, self.position) + +class Reader(object): + # Reader: + # - determines the data encoding and converts it to unicode, + # - checks if characters are in allowed range, + # - adds '\0' to the end. + + # Reader accepts + # - a `str` object, + # - a `unicode` object, + # - a file-like object with its `read` method returning `str`, + # - a file-like object with its `read` method returning `unicode`. + + # Yeah, it's ugly and slow. + + def __init__(self, stream): + self.name = None + self.stream = None + self.stream_pointer = 0 + self.eof = True + self.buffer = u'' + self.pointer = 0 + self.raw_buffer = None + self.raw_decode = None + self.encoding = None + self.index = 0 + self.line = 0 + self.column = 0 + if isinstance(stream, unicode): + self.name = "" + self.check_printable(stream) + self.buffer = stream+u'\0' + elif isinstance(stream, str): + self.name = "" + self.raw_buffer = stream + self.determine_encoding() + else: + self.stream = stream + self.name = getattr(stream, 'name', "") + self.eof = False + self.raw_buffer = '' + self.determine_encoding() + + def peek(self, index=0): + try: + return self.buffer[self.pointer+index] + except IndexError: + self.update(index+1) + return self.buffer[self.pointer+index] + + def prefix(self, length=1): + if self.pointer+length >= len(self.buffer): + self.update(length) + return self.buffer[self.pointer:self.pointer+length] + + def forward(self, length=1): + if self.pointer+length+1 >= len(self.buffer): + self.update(length+1) + while length: + ch = self.buffer[self.pointer] + self.pointer += 1 + self.index += 1 + if ch in u'\n\x85\u2028\u2029' \ + or (ch == u'\r' and self.buffer[self.pointer] != u'\n'): + self.line += 1 + self.column = 0 + elif ch != u'\uFEFF': + self.column += 1 + length -= 1 + + def get_mark(self): + if self.stream is None: + return Mark(self.name, self.index, self.line, self.column, + self.buffer, self.pointer) + else: + return Mark(self.name, self.index, self.line, self.column, + None, None) + + def determine_encoding(self): + while not self.eof and len(self.raw_buffer) < 2: + self.update_raw() + if not isinstance(self.raw_buffer, unicode): + if self.raw_buffer.startswith(codecs.BOM_UTF16_LE): + self.raw_decode = codecs.utf_16_le_decode + self.encoding = 'utf-16-le' + elif self.raw_buffer.startswith(codecs.BOM_UTF16_BE): + self.raw_decode = codecs.utf_16_be_decode + self.encoding = 'utf-16-be' + else: + self.raw_decode = codecs.utf_8_decode + self.encoding = 'utf-8' + self.update(1) + + if has_ucs4: + NON_PRINTABLE = u'[^\x09\x0A\x0D\x20-\x7E\x85\xA0-\uD7FF\uE000-\uFFFD\U00010000-\U0010ffff]' + elif sys.platform.startswith('java'): + # Jython doesn't support lone surrogates https://bugs.jython.org/issue2048 + NON_PRINTABLE = u'[^\x09\x0A\x0D\x20-\x7E\x85\xA0-\uD7FF\uE000-\uFFFD]' + else: + # Need to use eval here due to the above Jython issue + NON_PRINTABLE = eval(r"u'[^\x09\x0A\x0D\x20-\x7E\x85\xA0-\uFFFD]|(?:^|[^\uD800-\uDBFF])[\uDC00-\uDFFF]|[\uD800-\uDBFF](?:[^\uDC00-\uDFFF]|$)'") + NON_PRINTABLE = re.compile(NON_PRINTABLE) + def check_printable(self, data): + match = self.NON_PRINTABLE.search(data) + if match: + character = match.group() + position = self.index+(len(self.buffer)-self.pointer)+match.start() + raise ReaderError(self.name, position, ord(character), + 'unicode', "special characters are not allowed") + + def update(self, length): + if self.raw_buffer is None: + return + self.buffer = self.buffer[self.pointer:] + self.pointer = 0 + while len(self.buffer) < length: + if not self.eof: + self.update_raw() + if self.raw_decode is not None: + try: + data, converted = self.raw_decode(self.raw_buffer, + 'strict', self.eof) + except UnicodeDecodeError, exc: + character = exc.object[exc.start] + if self.stream is not None: + position = self.stream_pointer-len(self.raw_buffer)+exc.start + else: + position = exc.start + raise ReaderError(self.name, position, character, + exc.encoding, exc.reason) + else: + data = self.raw_buffer + converted = len(data) + self.check_printable(data) + self.buffer += data + self.raw_buffer = self.raw_buffer[converted:] + if self.eof: + self.buffer += u'\0' + self.raw_buffer = None + break + + def update_raw(self, size=1024): + data = self.stream.read(size) + if data: + self.raw_buffer += data + self.stream_pointer += len(data) + else: + self.eof = True diff --git a/third_party/python/PyYAML/lib/yaml/representer.py b/third_party/python/PyYAML/lib/yaml/representer.py new file mode 100644 index 0000000000..93e09b67b3 --- /dev/null +++ b/third_party/python/PyYAML/lib/yaml/representer.py @@ -0,0 +1,489 @@ + +__all__ = ['BaseRepresenter', 'SafeRepresenter', 'Representer', + 'RepresenterError'] + +from error import * + +from nodes import * + +import datetime + +import copy_reg, types + +class RepresenterError(YAMLError): + pass + +class BaseRepresenter(object): + + yaml_representers = {} + yaml_multi_representers = {} + + def __init__(self, default_style=None, default_flow_style=False, sort_keys=True): + self.default_style = default_style + self.default_flow_style = default_flow_style + self.sort_keys = sort_keys + self.represented_objects = {} + self.object_keeper = [] + self.alias_key = None + + def represent(self, data): + node = self.represent_data(data) + self.serialize(node) + self.represented_objects = {} + self.object_keeper = [] + self.alias_key = None + + def get_classobj_bases(self, cls): + bases = [cls] + for base in cls.__bases__: + bases.extend(self.get_classobj_bases(base)) + return bases + + def represent_data(self, data): + if self.ignore_aliases(data): + self.alias_key = None + else: + self.alias_key = id(data) + if self.alias_key is not None: + if self.alias_key in self.represented_objects: + node = self.represented_objects[self.alias_key] + #if node is None: + # raise RepresenterError("recursive objects are not allowed: %r" % data) + return node + #self.represented_objects[alias_key] = None + self.object_keeper.append(data) + data_types = type(data).__mro__ + if type(data) is types.InstanceType: + data_types = self.get_classobj_bases(data.__class__)+list(data_types) + if data_types[0] in self.yaml_representers: + node = self.yaml_representers[data_types[0]](self, data) + else: + for data_type in data_types: + if data_type in self.yaml_multi_representers: + node = self.yaml_multi_representers[data_type](self, data) + break + else: + if None in self.yaml_multi_representers: + node = self.yaml_multi_representers[None](self, data) + elif None in self.yaml_representers: + node = self.yaml_representers[None](self, data) + else: + node = ScalarNode(None, unicode(data)) + #if alias_key is not None: + # self.represented_objects[alias_key] = node + return node + + def add_representer(cls, data_type, representer): + if not 'yaml_representers' in cls.__dict__: + cls.yaml_representers = cls.yaml_representers.copy() + cls.yaml_representers[data_type] = representer + add_representer = classmethod(add_representer) + + def add_multi_representer(cls, data_type, representer): + if not 'yaml_multi_representers' in cls.__dict__: + cls.yaml_multi_representers = cls.yaml_multi_representers.copy() + cls.yaml_multi_representers[data_type] = representer + add_multi_representer = classmethod(add_multi_representer) + + def represent_scalar(self, tag, value, style=None): + if style is None: + style = self.default_style + node = ScalarNode(tag, value, style=style) + if self.alias_key is not None: + self.represented_objects[self.alias_key] = node + return node + + def represent_sequence(self, tag, sequence, flow_style=None): + value = [] + node = SequenceNode(tag, value, flow_style=flow_style) + if self.alias_key is not None: + self.represented_objects[self.alias_key] = node + best_style = True + for item in sequence: + node_item = self.represent_data(item) + if not (isinstance(node_item, ScalarNode) and not node_item.style): + best_style = False + value.append(node_item) + if flow_style is None: + if self.default_flow_style is not None: + node.flow_style = self.default_flow_style + else: + node.flow_style = best_style + return node + + def represent_mapping(self, tag, mapping, flow_style=None): + value = [] + node = MappingNode(tag, value, flow_style=flow_style) + if self.alias_key is not None: + self.represented_objects[self.alias_key] = node + best_style = True + if hasattr(mapping, 'items'): + mapping = mapping.items() + if self.sort_keys: + mapping.sort() + for item_key, item_value in mapping: + node_key = self.represent_data(item_key) + node_value = self.represent_data(item_value) + if not (isinstance(node_key, ScalarNode) and not node_key.style): + best_style = False + if not (isinstance(node_value, ScalarNode) and not node_value.style): + best_style = False + value.append((node_key, node_value)) + if flow_style is None: + if self.default_flow_style is not None: + node.flow_style = self.default_flow_style + else: + node.flow_style = best_style + return node + + def ignore_aliases(self, data): + return False + +class SafeRepresenter(BaseRepresenter): + + def ignore_aliases(self, data): + if data is None: + return True + if isinstance(data, tuple) and data == (): + return True + if isinstance(data, (str, unicode, bool, int, float)): + return True + + def represent_none(self, data): + return self.represent_scalar(u'tag:yaml.org,2002:null', + u'null') + + def represent_str(self, data): + tag = None + style = None + try: + data = unicode(data, 'ascii') + tag = u'tag:yaml.org,2002:str' + except UnicodeDecodeError: + try: + data = unicode(data, 'utf-8') + tag = u'tag:yaml.org,2002:str' + except UnicodeDecodeError: + data = data.encode('base64') + tag = u'tag:yaml.org,2002:binary' + style = '|' + return self.represent_scalar(tag, data, style=style) + + def represent_unicode(self, data): + return self.represent_scalar(u'tag:yaml.org,2002:str', data) + + def represent_bool(self, data): + if data: + value = u'true' + else: + value = u'false' + return self.represent_scalar(u'tag:yaml.org,2002:bool', value) + + def represent_int(self, data): + return self.represent_scalar(u'tag:yaml.org,2002:int', unicode(data)) + + def represent_long(self, data): + return self.represent_scalar(u'tag:yaml.org,2002:int', unicode(data)) + + inf_value = 1e300 + while repr(inf_value) != repr(inf_value*inf_value): + inf_value *= inf_value + + def represent_float(self, data): + if data != data or (data == 0.0 and data == 1.0): + value = u'.nan' + elif data == self.inf_value: + value = u'.inf' + elif data == -self.inf_value: + value = u'-.inf' + else: + value = unicode(repr(data)).lower() + # Note that in some cases `repr(data)` represents a float number + # without the decimal parts. For instance: + # >>> repr(1e17) + # '1e17' + # Unfortunately, this is not a valid float representation according + # to the definition of the `!!float` tag. We fix this by adding + # '.0' before the 'e' symbol. + if u'.' not in value and u'e' in value: + value = value.replace(u'e', u'.0e', 1) + return self.represent_scalar(u'tag:yaml.org,2002:float', value) + + def represent_list(self, data): + #pairs = (len(data) > 0 and isinstance(data, list)) + #if pairs: + # for item in data: + # if not isinstance(item, tuple) or len(item) != 2: + # pairs = False + # break + #if not pairs: + return self.represent_sequence(u'tag:yaml.org,2002:seq', data) + #value = [] + #for item_key, item_value in data: + # value.append(self.represent_mapping(u'tag:yaml.org,2002:map', + # [(item_key, item_value)])) + #return SequenceNode(u'tag:yaml.org,2002:pairs', value) + + def represent_dict(self, data): + return self.represent_mapping(u'tag:yaml.org,2002:map', data) + + def represent_set(self, data): + value = {} + for key in data: + value[key] = None + return self.represent_mapping(u'tag:yaml.org,2002:set', value) + + def represent_date(self, data): + value = unicode(data.isoformat()) + return self.represent_scalar(u'tag:yaml.org,2002:timestamp', value) + + def represent_datetime(self, data): + value = unicode(data.isoformat(' ')) + return self.represent_scalar(u'tag:yaml.org,2002:timestamp', value) + + def represent_yaml_object(self, tag, data, cls, flow_style=None): + if hasattr(data, '__getstate__'): + state = data.__getstate__() + else: + state = data.__dict__.copy() + return self.represent_mapping(tag, state, flow_style=flow_style) + + def represent_undefined(self, data): + raise RepresenterError("cannot represent an object", data) + +SafeRepresenter.add_representer(type(None), + SafeRepresenter.represent_none) + +SafeRepresenter.add_representer(str, + SafeRepresenter.represent_str) + +SafeRepresenter.add_representer(unicode, + SafeRepresenter.represent_unicode) + +SafeRepresenter.add_representer(bool, + SafeRepresenter.represent_bool) + +SafeRepresenter.add_representer(int, + SafeRepresenter.represent_int) + +SafeRepresenter.add_representer(long, + SafeRepresenter.represent_long) + +SafeRepresenter.add_representer(float, + SafeRepresenter.represent_float) + +SafeRepresenter.add_representer(list, + SafeRepresenter.represent_list) + +SafeRepresenter.add_representer(tuple, + SafeRepresenter.represent_list) + +SafeRepresenter.add_representer(dict, + SafeRepresenter.represent_dict) + +SafeRepresenter.add_representer(set, + SafeRepresenter.represent_set) + +SafeRepresenter.add_representer(datetime.date, + SafeRepresenter.represent_date) + +SafeRepresenter.add_representer(datetime.datetime, + SafeRepresenter.represent_datetime) + +SafeRepresenter.add_representer(None, + SafeRepresenter.represent_undefined) + +class Representer(SafeRepresenter): + + def represent_str(self, data): + tag = None + style = None + try: + data = unicode(data, 'ascii') + tag = u'tag:yaml.org,2002:str' + except UnicodeDecodeError: + try: + data = unicode(data, 'utf-8') + tag = u'tag:yaml.org,2002:python/str' + except UnicodeDecodeError: + data = data.encode('base64') + tag = u'tag:yaml.org,2002:binary' + style = '|' + return self.represent_scalar(tag, data, style=style) + + def represent_unicode(self, data): + tag = None + try: + data.encode('ascii') + tag = u'tag:yaml.org,2002:python/unicode' + except UnicodeEncodeError: + tag = u'tag:yaml.org,2002:str' + return self.represent_scalar(tag, data) + + def represent_long(self, data): + tag = u'tag:yaml.org,2002:int' + if int(data) is not data: + tag = u'tag:yaml.org,2002:python/long' + return self.represent_scalar(tag, unicode(data)) + + def represent_complex(self, data): + if data.imag == 0.0: + data = u'%r' % data.real + elif data.real == 0.0: + data = u'%rj' % data.imag + elif data.imag > 0: + data = u'%r+%rj' % (data.real, data.imag) + else: + data = u'%r%rj' % (data.real, data.imag) + return self.represent_scalar(u'tag:yaml.org,2002:python/complex', data) + + def represent_tuple(self, data): + return self.represent_sequence(u'tag:yaml.org,2002:python/tuple', data) + + def represent_name(self, data): + name = u'%s.%s' % (data.__module__, data.__name__) + return self.represent_scalar(u'tag:yaml.org,2002:python/name:'+name, u'') + + def represent_module(self, data): + return self.represent_scalar( + u'tag:yaml.org,2002:python/module:'+data.__name__, u'') + + def represent_instance(self, data): + # For instances of classic classes, we use __getinitargs__ and + # __getstate__ to serialize the data. + + # If data.__getinitargs__ exists, the object must be reconstructed by + # calling cls(**args), where args is a tuple returned by + # __getinitargs__. Otherwise, the cls.__init__ method should never be + # called and the class instance is created by instantiating a trivial + # class and assigning to the instance's __class__ variable. + + # If data.__getstate__ exists, it returns the state of the object. + # Otherwise, the state of the object is data.__dict__. + + # We produce either a !!python/object or !!python/object/new node. + # If data.__getinitargs__ does not exist and state is a dictionary, we + # produce a !!python/object node . Otherwise we produce a + # !!python/object/new node. + + cls = data.__class__ + class_name = u'%s.%s' % (cls.__module__, cls.__name__) + args = None + state = None + if hasattr(data, '__getinitargs__'): + args = list(data.__getinitargs__()) + if hasattr(data, '__getstate__'): + state = data.__getstate__() + else: + state = data.__dict__ + if args is None and isinstance(state, dict): + return self.represent_mapping( + u'tag:yaml.org,2002:python/object:'+class_name, state) + if isinstance(state, dict) and not state: + return self.represent_sequence( + u'tag:yaml.org,2002:python/object/new:'+class_name, args) + value = {} + if args: + value['args'] = args + value['state'] = state + return self.represent_mapping( + u'tag:yaml.org,2002:python/object/new:'+class_name, value) + + def represent_object(self, data): + # We use __reduce__ API to save the data. data.__reduce__ returns + # a tuple of length 2-5: + # (function, args, state, listitems, dictitems) + + # For reconstructing, we calls function(*args), then set its state, + # listitems, and dictitems if they are not None. + + # A special case is when function.__name__ == '__newobj__'. In this + # case we create the object with args[0].__new__(*args). + + # Another special case is when __reduce__ returns a string - we don't + # support it. + + # We produce a !!python/object, !!python/object/new or + # !!python/object/apply node. + + cls = type(data) + if cls in copy_reg.dispatch_table: + reduce = copy_reg.dispatch_table[cls](data) + elif hasattr(data, '__reduce_ex__'): + reduce = data.__reduce_ex__(2) + elif hasattr(data, '__reduce__'): + reduce = data.__reduce__() + else: + raise RepresenterError("cannot represent an object", data) + reduce = (list(reduce)+[None]*5)[:5] + function, args, state, listitems, dictitems = reduce + args = list(args) + if state is None: + state = {} + if listitems is not None: + listitems = list(listitems) + if dictitems is not None: + dictitems = dict(dictitems) + if function.__name__ == '__newobj__': + function = args[0] + args = args[1:] + tag = u'tag:yaml.org,2002:python/object/new:' + newobj = True + else: + tag = u'tag:yaml.org,2002:python/object/apply:' + newobj = False + function_name = u'%s.%s' % (function.__module__, function.__name__) + if not args and not listitems and not dictitems \ + and isinstance(state, dict) and newobj: + return self.represent_mapping( + u'tag:yaml.org,2002:python/object:'+function_name, state) + if not listitems and not dictitems \ + and isinstance(state, dict) and not state: + return self.represent_sequence(tag+function_name, args) + value = {} + if args: + value['args'] = args + if state or not isinstance(state, dict): + value['state'] = state + if listitems: + value['listitems'] = listitems + if dictitems: + value['dictitems'] = dictitems + return self.represent_mapping(tag+function_name, value) + +Representer.add_representer(str, + Representer.represent_str) + +Representer.add_representer(unicode, + Representer.represent_unicode) + +Representer.add_representer(long, + Representer.represent_long) + +Representer.add_representer(complex, + Representer.represent_complex) + +Representer.add_representer(tuple, + Representer.represent_tuple) + +Representer.add_representer(type, + Representer.represent_name) + +Representer.add_representer(types.ClassType, + Representer.represent_name) + +Representer.add_representer(types.FunctionType, + Representer.represent_name) + +Representer.add_representer(types.BuiltinFunctionType, + Representer.represent_name) + +Representer.add_representer(types.ModuleType, + Representer.represent_module) + +Representer.add_multi_representer(types.InstanceType, + Representer.represent_instance) + +Representer.add_multi_representer(object, + Representer.represent_object) + diff --git a/third_party/python/PyYAML/lib/yaml/resolver.py b/third_party/python/PyYAML/lib/yaml/resolver.py new file mode 100644 index 0000000000..ba9aeab21d --- /dev/null +++ b/third_party/python/PyYAML/lib/yaml/resolver.py @@ -0,0 +1,227 @@ + +__all__ = ['BaseResolver', 'Resolver'] + +from error import * +from nodes import * + +import re + +class ResolverError(YAMLError): + pass + +class BaseResolver(object): + + DEFAULT_SCALAR_TAG = u'tag:yaml.org,2002:str' + DEFAULT_SEQUENCE_TAG = u'tag:yaml.org,2002:seq' + DEFAULT_MAPPING_TAG = u'tag:yaml.org,2002:map' + + yaml_implicit_resolvers = {} + yaml_path_resolvers = {} + + def __init__(self): + self.resolver_exact_paths = [] + self.resolver_prefix_paths = [] + + def add_implicit_resolver(cls, tag, regexp, first): + if not 'yaml_implicit_resolvers' in cls.__dict__: + implicit_resolvers = {} + for key in cls.yaml_implicit_resolvers: + implicit_resolvers[key] = cls.yaml_implicit_resolvers[key][:] + cls.yaml_implicit_resolvers = implicit_resolvers + if first is None: + first = [None] + for ch in first: + cls.yaml_implicit_resolvers.setdefault(ch, []).append((tag, regexp)) + add_implicit_resolver = classmethod(add_implicit_resolver) + + def add_path_resolver(cls, tag, path, kind=None): + # Note: `add_path_resolver` is experimental. The API could be changed. + # `new_path` is a pattern that is matched against the path from the + # root to the node that is being considered. `node_path` elements are + # tuples `(node_check, index_check)`. `node_check` is a node class: + # `ScalarNode`, `SequenceNode`, `MappingNode` or `None`. `None` + # matches any kind of a node. `index_check` could be `None`, a boolean + # value, a string value, or a number. `None` and `False` match against + # any _value_ of sequence and mapping nodes. `True` matches against + # any _key_ of a mapping node. A string `index_check` matches against + # a mapping value that corresponds to a scalar key which content is + # equal to the `index_check` value. An integer `index_check` matches + # against a sequence value with the index equal to `index_check`. + if not 'yaml_path_resolvers' in cls.__dict__: + cls.yaml_path_resolvers = cls.yaml_path_resolvers.copy() + new_path = [] + for element in path: + if isinstance(element, (list, tuple)): + if len(element) == 2: + node_check, index_check = element + elif len(element) == 1: + node_check = element[0] + index_check = True + else: + raise ResolverError("Invalid path element: %s" % element) + else: + node_check = None + index_check = element + if node_check is str: + node_check = ScalarNode + elif node_check is list: + node_check = SequenceNode + elif node_check is dict: + node_check = MappingNode + elif node_check not in [ScalarNode, SequenceNode, MappingNode] \ + and not isinstance(node_check, basestring) \ + and node_check is not None: + raise ResolverError("Invalid node checker: %s" % node_check) + if not isinstance(index_check, (basestring, int)) \ + and index_check is not None: + raise ResolverError("Invalid index checker: %s" % index_check) + new_path.append((node_check, index_check)) + if kind is str: + kind = ScalarNode + elif kind is list: + kind = SequenceNode + elif kind is dict: + kind = MappingNode + elif kind not in [ScalarNode, SequenceNode, MappingNode] \ + and kind is not None: + raise ResolverError("Invalid node kind: %s" % kind) + cls.yaml_path_resolvers[tuple(new_path), kind] = tag + add_path_resolver = classmethod(add_path_resolver) + + def descend_resolver(self, current_node, current_index): + if not self.yaml_path_resolvers: + return + exact_paths = {} + prefix_paths = [] + if current_node: + depth = len(self.resolver_prefix_paths) + for path, kind in self.resolver_prefix_paths[-1]: + if self.check_resolver_prefix(depth, path, kind, + current_node, current_index): + if len(path) > depth: + prefix_paths.append((path, kind)) + else: + exact_paths[kind] = self.yaml_path_resolvers[path, kind] + else: + for path, kind in self.yaml_path_resolvers: + if not path: + exact_paths[kind] = self.yaml_path_resolvers[path, kind] + else: + prefix_paths.append((path, kind)) + self.resolver_exact_paths.append(exact_paths) + self.resolver_prefix_paths.append(prefix_paths) + + def ascend_resolver(self): + if not self.yaml_path_resolvers: + return + self.resolver_exact_paths.pop() + self.resolver_prefix_paths.pop() + + def check_resolver_prefix(self, depth, path, kind, + current_node, current_index): + node_check, index_check = path[depth-1] + if isinstance(node_check, basestring): + if current_node.tag != node_check: + return + elif node_check is not None: + if not isinstance(current_node, node_check): + return + if index_check is True and current_index is not None: + return + if (index_check is False or index_check is None) \ + and current_index is None: + return + if isinstance(index_check, basestring): + if not (isinstance(current_index, ScalarNode) + and index_check == current_index.value): + return + elif isinstance(index_check, int) and not isinstance(index_check, bool): + if index_check != current_index: + return + return True + + def resolve(self, kind, value, implicit): + if kind is ScalarNode and implicit[0]: + if value == u'': + resolvers = self.yaml_implicit_resolvers.get(u'', []) + else: + resolvers = self.yaml_implicit_resolvers.get(value[0], []) + wildcard_resolvers = self.yaml_implicit_resolvers.get(None, []) + for tag, regexp in resolvers + wildcard_resolvers: + if regexp.match(value): + return tag + implicit = implicit[1] + if self.yaml_path_resolvers: + exact_paths = self.resolver_exact_paths[-1] + if kind in exact_paths: + return exact_paths[kind] + if None in exact_paths: + return exact_paths[None] + if kind is ScalarNode: + return self.DEFAULT_SCALAR_TAG + elif kind is SequenceNode: + return self.DEFAULT_SEQUENCE_TAG + elif kind is MappingNode: + return self.DEFAULT_MAPPING_TAG + +class Resolver(BaseResolver): + pass + +Resolver.add_implicit_resolver( + u'tag:yaml.org,2002:bool', + re.compile(ur'''^(?:yes|Yes|YES|no|No|NO + |true|True|TRUE|false|False|FALSE + |on|On|ON|off|Off|OFF)$''', re.X), + list(u'yYnNtTfFoO')) + +Resolver.add_implicit_resolver( + u'tag:yaml.org,2002:float', + re.compile(ur'''^(?:[-+]?(?:[0-9][0-9_]*)\.[0-9_]*(?:[eE][-+][0-9]+)? + |\.[0-9_]+(?:[eE][-+][0-9]+)? + |[-+]?[0-9][0-9_]*(?::[0-5]?[0-9])+\.[0-9_]* + |[-+]?\.(?:inf|Inf|INF) + |\.(?:nan|NaN|NAN))$''', re.X), + list(u'-+0123456789.')) + +Resolver.add_implicit_resolver( + u'tag:yaml.org,2002:int', + re.compile(ur'''^(?:[-+]?0b[0-1_]+ + |[-+]?0[0-7_]+ + |[-+]?(?:0|[1-9][0-9_]*) + |[-+]?0x[0-9a-fA-F_]+ + |[-+]?[1-9][0-9_]*(?::[0-5]?[0-9])+)$''', re.X), + list(u'-+0123456789')) + +Resolver.add_implicit_resolver( + u'tag:yaml.org,2002:merge', + re.compile(ur'^(?:<<)$'), + [u'<']) + +Resolver.add_implicit_resolver( + u'tag:yaml.org,2002:null', + re.compile(ur'''^(?: ~ + |null|Null|NULL + | )$''', re.X), + [u'~', u'n', u'N', u'']) + +Resolver.add_implicit_resolver( + u'tag:yaml.org,2002:timestamp', + re.compile(ur'''^(?:[0-9][0-9][0-9][0-9]-[0-9][0-9]-[0-9][0-9] + |[0-9][0-9][0-9][0-9] -[0-9][0-9]? -[0-9][0-9]? + (?:[Tt]|[ \t]+)[0-9][0-9]? + :[0-9][0-9] :[0-9][0-9] (?:\.[0-9]*)? + (?:[ \t]*(?:Z|[-+][0-9][0-9]?(?::[0-9][0-9])?))?)$''', re.X), + list(u'0123456789')) + +Resolver.add_implicit_resolver( + u'tag:yaml.org,2002:value', + re.compile(ur'^(?:=)$'), + [u'=']) + +# The following resolver is only for documentation purposes. It cannot work +# because plain scalars cannot start with '!', '&', or '*'. +Resolver.add_implicit_resolver( + u'tag:yaml.org,2002:yaml', + re.compile(ur'^(?:!|&|\*)$'), + list(u'!&*')) + diff --git a/third_party/python/PyYAML/lib/yaml/scanner.py b/third_party/python/PyYAML/lib/yaml/scanner.py new file mode 100644 index 0000000000..098ea7be82 --- /dev/null +++ b/third_party/python/PyYAML/lib/yaml/scanner.py @@ -0,0 +1,1444 @@ + +# Scanner produces tokens of the following types: +# STREAM-START +# STREAM-END +# DIRECTIVE(name, value) +# DOCUMENT-START +# DOCUMENT-END +# BLOCK-SEQUENCE-START +# BLOCK-MAPPING-START +# BLOCK-END +# FLOW-SEQUENCE-START +# FLOW-MAPPING-START +# FLOW-SEQUENCE-END +# FLOW-MAPPING-END +# BLOCK-ENTRY +# FLOW-ENTRY +# KEY +# VALUE +# ALIAS(value) +# ANCHOR(value) +# TAG(value) +# SCALAR(value, plain, style) +# +# Read comments in the Scanner code for more details. +# + +__all__ = ['Scanner', 'ScannerError'] + +from error import MarkedYAMLError +from tokens import * + +class ScannerError(MarkedYAMLError): + pass + +class SimpleKey(object): + # See below simple keys treatment. + + def __init__(self, token_number, required, index, line, column, mark): + self.token_number = token_number + self.required = required + self.index = index + self.line = line + self.column = column + self.mark = mark + +class Scanner(object): + + def __init__(self): + """Initialize the scanner.""" + # It is assumed that Scanner and Reader will have a common descendant. + # Reader do the dirty work of checking for BOM and converting the + # input data to Unicode. It also adds NUL to the end. + # + # Reader supports the following methods + # self.peek(i=0) # peek the next i-th character + # self.prefix(l=1) # peek the next l characters + # self.forward(l=1) # read the next l characters and move the pointer. + + # Had we reached the end of the stream? + self.done = False + + # The number of unclosed '{' and '['. `flow_level == 0` means block + # context. + self.flow_level = 0 + + # List of processed tokens that are not yet emitted. + self.tokens = [] + + # Add the STREAM-START token. + self.fetch_stream_start() + + # Number of tokens that were emitted through the `get_token` method. + self.tokens_taken = 0 + + # The current indentation level. + self.indent = -1 + + # Past indentation levels. + self.indents = [] + + # Variables related to simple keys treatment. + + # A simple key is a key that is not denoted by the '?' indicator. + # Example of simple keys: + # --- + # block simple key: value + # ? not a simple key: + # : { flow simple key: value } + # We emit the KEY token before all keys, so when we find a potential + # simple key, we try to locate the corresponding ':' indicator. + # Simple keys should be limited to a single line and 1024 characters. + + # Can a simple key start at the current position? A simple key may + # start: + # - at the beginning of the line, not counting indentation spaces + # (in block context), + # - after '{', '[', ',' (in the flow context), + # - after '?', ':', '-' (in the block context). + # In the block context, this flag also signifies if a block collection + # may start at the current position. + self.allow_simple_key = True + + # Keep track of possible simple keys. This is a dictionary. The key + # is `flow_level`; there can be no more that one possible simple key + # for each level. The value is a SimpleKey record: + # (token_number, required, index, line, column, mark) + # A simple key may start with ALIAS, ANCHOR, TAG, SCALAR(flow), + # '[', or '{' tokens. + self.possible_simple_keys = {} + + # Public methods. + + def check_token(self, *choices): + # Check if the next token is one of the given types. + while self.need_more_tokens(): + self.fetch_more_tokens() + if self.tokens: + if not choices: + return True + for choice in choices: + if isinstance(self.tokens[0], choice): + return True + return False + + def peek_token(self): + # Return the next token, but do not delete if from the queue. + # Return None if no more tokens. + while self.need_more_tokens(): + self.fetch_more_tokens() + if self.tokens: + return self.tokens[0] + else: + return None + + def get_token(self): + # Return the next token. + while self.need_more_tokens(): + self.fetch_more_tokens() + if self.tokens: + self.tokens_taken += 1 + return self.tokens.pop(0) + + # Private methods. + + def need_more_tokens(self): + if self.done: + return False + if not self.tokens: + return True + # The current token may be a potential simple key, so we + # need to look further. + self.stale_possible_simple_keys() + if self.next_possible_simple_key() == self.tokens_taken: + return True + + def fetch_more_tokens(self): + + # Eat whitespaces and comments until we reach the next token. + self.scan_to_next_token() + + # Remove obsolete possible simple keys. + self.stale_possible_simple_keys() + + # Compare the current indentation and column. It may add some tokens + # and decrease the current indentation level. + self.unwind_indent(self.column) + + # Peek the next character. + ch = self.peek() + + # Is it the end of stream? + if ch == u'\0': + return self.fetch_stream_end() + + # Is it a directive? + if ch == u'%' and self.check_directive(): + return self.fetch_directive() + + # Is it the document start? + if ch == u'-' and self.check_document_start(): + return self.fetch_document_start() + + # Is it the document end? + if ch == u'.' and self.check_document_end(): + return self.fetch_document_end() + + # TODO: support for BOM within a stream. + #if ch == u'\uFEFF': + # return self.fetch_bom() <-- issue BOMToken + + # Note: the order of the following checks is NOT significant. + + # Is it the flow sequence start indicator? + if ch == u'[': + return self.fetch_flow_sequence_start() + + # Is it the flow mapping start indicator? + if ch == u'{': + return self.fetch_flow_mapping_start() + + # Is it the flow sequence end indicator? + if ch == u']': + return self.fetch_flow_sequence_end() + + # Is it the flow mapping end indicator? + if ch == u'}': + return self.fetch_flow_mapping_end() + + # Is it the flow entry indicator? + if ch == u',': + return self.fetch_flow_entry() + + # Is it the block entry indicator? + if ch == u'-' and self.check_block_entry(): + return self.fetch_block_entry() + + # Is it the key indicator? + if ch == u'?' and self.check_key(): + return self.fetch_key() + + # Is it the value indicator? + if ch == u':' and self.check_value(): + return self.fetch_value() + + # Is it an alias? + if ch == u'*': + return self.fetch_alias() + + # Is it an anchor? + if ch == u'&': + return self.fetch_anchor() + + # Is it a tag? + if ch == u'!': + return self.fetch_tag() + + # Is it a literal scalar? + if ch == u'|' and not self.flow_level: + return self.fetch_literal() + + # Is it a folded scalar? + if ch == u'>' and not self.flow_level: + return self.fetch_folded() + + # Is it a single quoted scalar? + if ch == u'\'': + return self.fetch_single() + + # Is it a double quoted scalar? + if ch == u'\"': + return self.fetch_double() + + # It must be a plain scalar then. + if self.check_plain(): + return self.fetch_plain() + + # No? It's an error. Let's produce a nice error message. + raise ScannerError("while scanning for the next token", None, + "found character %r that cannot start any token" + % ch.encode('utf-8'), self.get_mark()) + + # Simple keys treatment. + + def next_possible_simple_key(self): + # Return the number of the nearest possible simple key. Actually we + # don't need to loop through the whole dictionary. We may replace it + # with the following code: + # if not self.possible_simple_keys: + # return None + # return self.possible_simple_keys[ + # min(self.possible_simple_keys.keys())].token_number + min_token_number = None + for level in self.possible_simple_keys: + key = self.possible_simple_keys[level] + if min_token_number is None or key.token_number < min_token_number: + min_token_number = key.token_number + return min_token_number + + def stale_possible_simple_keys(self): + # Remove entries that are no longer possible simple keys. According to + # the YAML specification, simple keys + # - should be limited to a single line, + # - should be no longer than 1024 characters. + # Disabling this procedure will allow simple keys of any length and + # height (may cause problems if indentation is broken though). + for level in self.possible_simple_keys.keys(): + key = self.possible_simple_keys[level] + if key.line != self.line \ + or self.index-key.index > 1024: + if key.required: + raise ScannerError("while scanning a simple key", key.mark, + "could not find expected ':'", self.get_mark()) + del self.possible_simple_keys[level] + + def save_possible_simple_key(self): + # The next token may start a simple key. We check if it's possible + # and save its position. This function is called for + # ALIAS, ANCHOR, TAG, SCALAR(flow), '[', and '{'. + + # Check if a simple key is required at the current position. + required = not self.flow_level and self.indent == self.column + + # The next token might be a simple key. Let's save it's number and + # position. + if self.allow_simple_key: + self.remove_possible_simple_key() + token_number = self.tokens_taken+len(self.tokens) + key = SimpleKey(token_number, required, + self.index, self.line, self.column, self.get_mark()) + self.possible_simple_keys[self.flow_level] = key + + def remove_possible_simple_key(self): + # Remove the saved possible key position at the current flow level. + if self.flow_level in self.possible_simple_keys: + key = self.possible_simple_keys[self.flow_level] + + if key.required: + raise ScannerError("while scanning a simple key", key.mark, + "could not find expected ':'", self.get_mark()) + + del self.possible_simple_keys[self.flow_level] + + # Indentation functions. + + def unwind_indent(self, column): + + ## In flow context, tokens should respect indentation. + ## Actually the condition should be `self.indent >= column` according to + ## the spec. But this condition will prohibit intuitively correct + ## constructions such as + ## key : { + ## } + #if self.flow_level and self.indent > column: + # raise ScannerError(None, None, + # "invalid indentation or unclosed '[' or '{'", + # self.get_mark()) + + # In the flow context, indentation is ignored. We make the scanner less + # restrictive then specification requires. + if self.flow_level: + return + + # In block context, we may need to issue the BLOCK-END tokens. + while self.indent > column: + mark = self.get_mark() + self.indent = self.indents.pop() + self.tokens.append(BlockEndToken(mark, mark)) + + def add_indent(self, column): + # Check if we need to increase indentation. + if self.indent < column: + self.indents.append(self.indent) + self.indent = column + return True + return False + + # Fetchers. + + def fetch_stream_start(self): + # We always add STREAM-START as the first token and STREAM-END as the + # last token. + + # Read the token. + mark = self.get_mark() + + # Add STREAM-START. + self.tokens.append(StreamStartToken(mark, mark, + encoding=self.encoding)) + + + def fetch_stream_end(self): + + # Set the current indentation to -1. + self.unwind_indent(-1) + + # Reset simple keys. + self.remove_possible_simple_key() + self.allow_simple_key = False + self.possible_simple_keys = {} + + # Read the token. + mark = self.get_mark() + + # Add STREAM-END. + self.tokens.append(StreamEndToken(mark, mark)) + + # The steam is finished. + self.done = True + + def fetch_directive(self): + + # Set the current indentation to -1. + self.unwind_indent(-1) + + # Reset simple keys. + self.remove_possible_simple_key() + self.allow_simple_key = False + + # Scan and add DIRECTIVE. + self.tokens.append(self.scan_directive()) + + def fetch_document_start(self): + self.fetch_document_indicator(DocumentStartToken) + + def fetch_document_end(self): + self.fetch_document_indicator(DocumentEndToken) + + def fetch_document_indicator(self, TokenClass): + + # Set the current indentation to -1. + self.unwind_indent(-1) + + # Reset simple keys. Note that there could not be a block collection + # after '---'. + self.remove_possible_simple_key() + self.allow_simple_key = False + + # Add DOCUMENT-START or DOCUMENT-END. + start_mark = self.get_mark() + self.forward(3) + end_mark = self.get_mark() + self.tokens.append(TokenClass(start_mark, end_mark)) + + def fetch_flow_sequence_start(self): + self.fetch_flow_collection_start(FlowSequenceStartToken) + + def fetch_flow_mapping_start(self): + self.fetch_flow_collection_start(FlowMappingStartToken) + + def fetch_flow_collection_start(self, TokenClass): + + # '[' and '{' may start a simple key. + self.save_possible_simple_key() + + # Increase the flow level. + self.flow_level += 1 + + # Simple keys are allowed after '[' and '{'. + self.allow_simple_key = True + + # Add FLOW-SEQUENCE-START or FLOW-MAPPING-START. + start_mark = self.get_mark() + self.forward() + end_mark = self.get_mark() + self.tokens.append(TokenClass(start_mark, end_mark)) + + def fetch_flow_sequence_end(self): + self.fetch_flow_collection_end(FlowSequenceEndToken) + + def fetch_flow_mapping_end(self): + self.fetch_flow_collection_end(FlowMappingEndToken) + + def fetch_flow_collection_end(self, TokenClass): + + # Reset possible simple key on the current level. + self.remove_possible_simple_key() + + # Decrease the flow level. + self.flow_level -= 1 + + # No simple keys after ']' or '}'. + self.allow_simple_key = False + + # Add FLOW-SEQUENCE-END or FLOW-MAPPING-END. + start_mark = self.get_mark() + self.forward() + end_mark = self.get_mark() + self.tokens.append(TokenClass(start_mark, end_mark)) + + def fetch_flow_entry(self): + + # Simple keys are allowed after ','. + self.allow_simple_key = True + + # Reset possible simple key on the current level. + self.remove_possible_simple_key() + + # Add FLOW-ENTRY. + start_mark = self.get_mark() + self.forward() + end_mark = self.get_mark() + self.tokens.append(FlowEntryToken(start_mark, end_mark)) + + def fetch_block_entry(self): + + # Block context needs additional checks. + if not self.flow_level: + + # Are we allowed to start a new entry? + if not self.allow_simple_key: + raise ScannerError(None, None, + "sequence entries are not allowed here", + self.get_mark()) + + # We may need to add BLOCK-SEQUENCE-START. + if self.add_indent(self.column): + mark = self.get_mark() + self.tokens.append(BlockSequenceStartToken(mark, mark)) + + # It's an error for the block entry to occur in the flow context, + # but we let the parser detect this. + else: + pass + + # Simple keys are allowed after '-'. + self.allow_simple_key = True + + # Reset possible simple key on the current level. + self.remove_possible_simple_key() + + # Add BLOCK-ENTRY. + start_mark = self.get_mark() + self.forward() + end_mark = self.get_mark() + self.tokens.append(BlockEntryToken(start_mark, end_mark)) + + def fetch_key(self): + + # Block context needs additional checks. + if not self.flow_level: + + # Are we allowed to start a key (not necessary a simple)? + if not self.allow_simple_key: + raise ScannerError(None, None, + "mapping keys are not allowed here", + self.get_mark()) + + # We may need to add BLOCK-MAPPING-START. + if self.add_indent(self.column): + mark = self.get_mark() + self.tokens.append(BlockMappingStartToken(mark, mark)) + + # Simple keys are allowed after '?' in the block context. + self.allow_simple_key = not self.flow_level + + # Reset possible simple key on the current level. + self.remove_possible_simple_key() + + # Add KEY. + start_mark = self.get_mark() + self.forward() + end_mark = self.get_mark() + self.tokens.append(KeyToken(start_mark, end_mark)) + + def fetch_value(self): + + # Do we determine a simple key? + if self.flow_level in self.possible_simple_keys: + + # Add KEY. + key = self.possible_simple_keys[self.flow_level] + del self.possible_simple_keys[self.flow_level] + self.tokens.insert(key.token_number-self.tokens_taken, + KeyToken(key.mark, key.mark)) + + # If this key starts a new block mapping, we need to add + # BLOCK-MAPPING-START. + if not self.flow_level: + if self.add_indent(key.column): + self.tokens.insert(key.token_number-self.tokens_taken, + BlockMappingStartToken(key.mark, key.mark)) + + # There cannot be two simple keys one after another. + self.allow_simple_key = False + + # It must be a part of a complex key. + else: + + # Block context needs additional checks. + # (Do we really need them? They will be caught by the parser + # anyway.) + if not self.flow_level: + + # We are allowed to start a complex value if and only if + # we can start a simple key. + if not self.allow_simple_key: + raise ScannerError(None, None, + "mapping values are not allowed here", + self.get_mark()) + + # If this value starts a new block mapping, we need to add + # BLOCK-MAPPING-START. It will be detected as an error later by + # the parser. + if not self.flow_level: + if self.add_indent(self.column): + mark = self.get_mark() + self.tokens.append(BlockMappingStartToken(mark, mark)) + + # Simple keys are allowed after ':' in the block context. + self.allow_simple_key = not self.flow_level + + # Reset possible simple key on the current level. + self.remove_possible_simple_key() + + # Add VALUE. + start_mark = self.get_mark() + self.forward() + end_mark = self.get_mark() + self.tokens.append(ValueToken(start_mark, end_mark)) + + def fetch_alias(self): + + # ALIAS could be a simple key. + self.save_possible_simple_key() + + # No simple keys after ALIAS. + self.allow_simple_key = False + + # Scan and add ALIAS. + self.tokens.append(self.scan_anchor(AliasToken)) + + def fetch_anchor(self): + + # ANCHOR could start a simple key. + self.save_possible_simple_key() + + # No simple keys after ANCHOR. + self.allow_simple_key = False + + # Scan and add ANCHOR. + self.tokens.append(self.scan_anchor(AnchorToken)) + + def fetch_tag(self): + + # TAG could start a simple key. + self.save_possible_simple_key() + + # No simple keys after TAG. + self.allow_simple_key = False + + # Scan and add TAG. + self.tokens.append(self.scan_tag()) + + def fetch_literal(self): + self.fetch_block_scalar(style='|') + + def fetch_folded(self): + self.fetch_block_scalar(style='>') + + def fetch_block_scalar(self, style): + + # A simple key may follow a block scalar. + self.allow_simple_key = True + + # Reset possible simple key on the current level. + self.remove_possible_simple_key() + + # Scan and add SCALAR. + self.tokens.append(self.scan_block_scalar(style)) + + def fetch_single(self): + self.fetch_flow_scalar(style='\'') + + def fetch_double(self): + self.fetch_flow_scalar(style='"') + + def fetch_flow_scalar(self, style): + + # A flow scalar could be a simple key. + self.save_possible_simple_key() + + # No simple keys after flow scalars. + self.allow_simple_key = False + + # Scan and add SCALAR. + self.tokens.append(self.scan_flow_scalar(style)) + + def fetch_plain(self): + + # A plain scalar could be a simple key. + self.save_possible_simple_key() + + # No simple keys after plain scalars. But note that `scan_plain` will + # change this flag if the scan is finished at the beginning of the + # line. + self.allow_simple_key = False + + # Scan and add SCALAR. May change `allow_simple_key`. + self.tokens.append(self.scan_plain()) + + # Checkers. + + def check_directive(self): + + # DIRECTIVE: ^ '%' ... + # The '%' indicator is already checked. + if self.column == 0: + return True + + def check_document_start(self): + + # DOCUMENT-START: ^ '---' (' '|'\n') + if self.column == 0: + if self.prefix(3) == u'---' \ + and self.peek(3) in u'\0 \t\r\n\x85\u2028\u2029': + return True + + def check_document_end(self): + + # DOCUMENT-END: ^ '...' (' '|'\n') + if self.column == 0: + if self.prefix(3) == u'...' \ + and self.peek(3) in u'\0 \t\r\n\x85\u2028\u2029': + return True + + def check_block_entry(self): + + # BLOCK-ENTRY: '-' (' '|'\n') + return self.peek(1) in u'\0 \t\r\n\x85\u2028\u2029' + + def check_key(self): + + # KEY(flow context): '?' + if self.flow_level: + return True + + # KEY(block context): '?' (' '|'\n') + else: + return self.peek(1) in u'\0 \t\r\n\x85\u2028\u2029' + + def check_value(self): + + # VALUE(flow context): ':' + if self.flow_level: + return True + + # VALUE(block context): ':' (' '|'\n') + else: + return self.peek(1) in u'\0 \t\r\n\x85\u2028\u2029' + + def check_plain(self): + + # A plain scalar may start with any non-space character except: + # '-', '?', ':', ',', '[', ']', '{', '}', + # '#', '&', '*', '!', '|', '>', '\'', '\"', + # '%', '@', '`'. + # + # It may also start with + # '-', '?', ':' + # if it is followed by a non-space character. + # + # Note that we limit the last rule to the block context (except the + # '-' character) because we want the flow context to be space + # independent. + ch = self.peek() + return ch not in u'\0 \t\r\n\x85\u2028\u2029-?:,[]{}#&*!|>\'\"%@`' \ + or (self.peek(1) not in u'\0 \t\r\n\x85\u2028\u2029' + and (ch == u'-' or (not self.flow_level and ch in u'?:'))) + + # Scanners. + + def scan_to_next_token(self): + # We ignore spaces, line breaks and comments. + # If we find a line break in the block context, we set the flag + # `allow_simple_key` on. + # The byte order mark is stripped if it's the first character in the + # stream. We do not yet support BOM inside the stream as the + # specification requires. Any such mark will be considered as a part + # of the document. + # + # TODO: We need to make tab handling rules more sane. A good rule is + # Tabs cannot precede tokens + # BLOCK-SEQUENCE-START, BLOCK-MAPPING-START, BLOCK-END, + # KEY(block), VALUE(block), BLOCK-ENTRY + # So the checking code is + # if : + # self.allow_simple_keys = False + # We also need to add the check for `allow_simple_keys == True` to + # `unwind_indent` before issuing BLOCK-END. + # Scanners for block, flow, and plain scalars need to be modified. + + if self.index == 0 and self.peek() == u'\uFEFF': + self.forward() + found = False + while not found: + while self.peek() == u' ': + self.forward() + if self.peek() == u'#': + while self.peek() not in u'\0\r\n\x85\u2028\u2029': + self.forward() + if self.scan_line_break(): + if not self.flow_level: + self.allow_simple_key = True + else: + found = True + + def scan_directive(self): + # See the specification for details. + start_mark = self.get_mark() + self.forward() + name = self.scan_directive_name(start_mark) + value = None + if name == u'YAML': + value = self.scan_yaml_directive_value(start_mark) + end_mark = self.get_mark() + elif name == u'TAG': + value = self.scan_tag_directive_value(start_mark) + end_mark = self.get_mark() + else: + end_mark = self.get_mark() + while self.peek() not in u'\0\r\n\x85\u2028\u2029': + self.forward() + self.scan_directive_ignored_line(start_mark) + return DirectiveToken(name, value, start_mark, end_mark) + + def scan_directive_name(self, start_mark): + # See the specification for details. + length = 0 + ch = self.peek(length) + while u'0' <= ch <= u'9' or u'A' <= ch <= u'Z' or u'a' <= ch <= u'z' \ + or ch in u'-_': + length += 1 + ch = self.peek(length) + if not length: + raise ScannerError("while scanning a directive", start_mark, + "expected alphabetic or numeric character, but found %r" + % ch.encode('utf-8'), self.get_mark()) + value = self.prefix(length) + self.forward(length) + ch = self.peek() + if ch not in u'\0 \r\n\x85\u2028\u2029': + raise ScannerError("while scanning a directive", start_mark, + "expected alphabetic or numeric character, but found %r" + % ch.encode('utf-8'), self.get_mark()) + return value + + def scan_yaml_directive_value(self, start_mark): + # See the specification for details. + while self.peek() == u' ': + self.forward() + major = self.scan_yaml_directive_number(start_mark) + if self.peek() != '.': + raise ScannerError("while scanning a directive", start_mark, + "expected a digit or '.', but found %r" + % self.peek().encode('utf-8'), + self.get_mark()) + self.forward() + minor = self.scan_yaml_directive_number(start_mark) + if self.peek() not in u'\0 \r\n\x85\u2028\u2029': + raise ScannerError("while scanning a directive", start_mark, + "expected a digit or ' ', but found %r" + % self.peek().encode('utf-8'), + self.get_mark()) + return (major, minor) + + def scan_yaml_directive_number(self, start_mark): + # See the specification for details. + ch = self.peek() + if not (u'0' <= ch <= u'9'): + raise ScannerError("while scanning a directive", start_mark, + "expected a digit, but found %r" % ch.encode('utf-8'), + self.get_mark()) + length = 0 + while u'0' <= self.peek(length) <= u'9': + length += 1 + value = int(self.prefix(length)) + self.forward(length) + return value + + def scan_tag_directive_value(self, start_mark): + # See the specification for details. + while self.peek() == u' ': + self.forward() + handle = self.scan_tag_directive_handle(start_mark) + while self.peek() == u' ': + self.forward() + prefix = self.scan_tag_directive_prefix(start_mark) + return (handle, prefix) + + def scan_tag_directive_handle(self, start_mark): + # See the specification for details. + value = self.scan_tag_handle('directive', start_mark) + ch = self.peek() + if ch != u' ': + raise ScannerError("while scanning a directive", start_mark, + "expected ' ', but found %r" % ch.encode('utf-8'), + self.get_mark()) + return value + + def scan_tag_directive_prefix(self, start_mark): + # See the specification for details. + value = self.scan_tag_uri('directive', start_mark) + ch = self.peek() + if ch not in u'\0 \r\n\x85\u2028\u2029': + raise ScannerError("while scanning a directive", start_mark, + "expected ' ', but found %r" % ch.encode('utf-8'), + self.get_mark()) + return value + + def scan_directive_ignored_line(self, start_mark): + # See the specification for details. + while self.peek() == u' ': + self.forward() + if self.peek() == u'#': + while self.peek() not in u'\0\r\n\x85\u2028\u2029': + self.forward() + ch = self.peek() + if ch not in u'\0\r\n\x85\u2028\u2029': + raise ScannerError("while scanning a directive", start_mark, + "expected a comment or a line break, but found %r" + % ch.encode('utf-8'), self.get_mark()) + self.scan_line_break() + + def scan_anchor(self, TokenClass): + # The specification does not restrict characters for anchors and + # aliases. This may lead to problems, for instance, the document: + # [ *alias, value ] + # can be interpreted in two ways, as + # [ "value" ] + # and + # [ *alias , "value" ] + # Therefore we restrict aliases to numbers and ASCII letters. + start_mark = self.get_mark() + indicator = self.peek() + if indicator == u'*': + name = 'alias' + else: + name = 'anchor' + self.forward() + length = 0 + ch = self.peek(length) + while u'0' <= ch <= u'9' or u'A' <= ch <= u'Z' or u'a' <= ch <= u'z' \ + or ch in u'-_': + length += 1 + ch = self.peek(length) + if not length: + raise ScannerError("while scanning an %s" % name, start_mark, + "expected alphabetic or numeric character, but found %r" + % ch.encode('utf-8'), self.get_mark()) + value = self.prefix(length) + self.forward(length) + ch = self.peek() + if ch not in u'\0 \t\r\n\x85\u2028\u2029?:,]}%@`': + raise ScannerError("while scanning an %s" % name, start_mark, + "expected alphabetic or numeric character, but found %r" + % ch.encode('utf-8'), self.get_mark()) + end_mark = self.get_mark() + return TokenClass(value, start_mark, end_mark) + + def scan_tag(self): + # See the specification for details. + start_mark = self.get_mark() + ch = self.peek(1) + if ch == u'<': + handle = None + self.forward(2) + suffix = self.scan_tag_uri('tag', start_mark) + if self.peek() != u'>': + raise ScannerError("while parsing a tag", start_mark, + "expected '>', but found %r" % self.peek().encode('utf-8'), + self.get_mark()) + self.forward() + elif ch in u'\0 \t\r\n\x85\u2028\u2029': + handle = None + suffix = u'!' + self.forward() + else: + length = 1 + use_handle = False + while ch not in u'\0 \r\n\x85\u2028\u2029': + if ch == u'!': + use_handle = True + break + length += 1 + ch = self.peek(length) + handle = u'!' + if use_handle: + handle = self.scan_tag_handle('tag', start_mark) + else: + handle = u'!' + self.forward() + suffix = self.scan_tag_uri('tag', start_mark) + ch = self.peek() + if ch not in u'\0 \r\n\x85\u2028\u2029': + raise ScannerError("while scanning a tag", start_mark, + "expected ' ', but found %r" % ch.encode('utf-8'), + self.get_mark()) + value = (handle, suffix) + end_mark = self.get_mark() + return TagToken(value, start_mark, end_mark) + + def scan_block_scalar(self, style): + # See the specification for details. + + if style == '>': + folded = True + else: + folded = False + + chunks = [] + start_mark = self.get_mark() + + # Scan the header. + self.forward() + chomping, increment = self.scan_block_scalar_indicators(start_mark) + self.scan_block_scalar_ignored_line(start_mark) + + # Determine the indentation level and go to the first non-empty line. + min_indent = self.indent+1 + if min_indent < 1: + min_indent = 1 + if increment is None: + breaks, max_indent, end_mark = self.scan_block_scalar_indentation() + indent = max(min_indent, max_indent) + else: + indent = min_indent+increment-1 + breaks, end_mark = self.scan_block_scalar_breaks(indent) + line_break = u'' + + # Scan the inner part of the block scalar. + while self.column == indent and self.peek() != u'\0': + chunks.extend(breaks) + leading_non_space = self.peek() not in u' \t' + length = 0 + while self.peek(length) not in u'\0\r\n\x85\u2028\u2029': + length += 1 + chunks.append(self.prefix(length)) + self.forward(length) + line_break = self.scan_line_break() + breaks, end_mark = self.scan_block_scalar_breaks(indent) + if self.column == indent and self.peek() != u'\0': + + # Unfortunately, folding rules are ambiguous. + # + # This is the folding according to the specification: + + if folded and line_break == u'\n' \ + and leading_non_space and self.peek() not in u' \t': + if not breaks: + chunks.append(u' ') + else: + chunks.append(line_break) + + # This is Clark Evans's interpretation (also in the spec + # examples): + # + #if folded and line_break == u'\n': + # if not breaks: + # if self.peek() not in ' \t': + # chunks.append(u' ') + # else: + # chunks.append(line_break) + #else: + # chunks.append(line_break) + else: + break + + # Chomp the tail. + if chomping is not False: + chunks.append(line_break) + if chomping is True: + chunks.extend(breaks) + + # We are done. + return ScalarToken(u''.join(chunks), False, start_mark, end_mark, + style) + + def scan_block_scalar_indicators(self, start_mark): + # See the specification for details. + chomping = None + increment = None + ch = self.peek() + if ch in u'+-': + if ch == '+': + chomping = True + else: + chomping = False + self.forward() + ch = self.peek() + if ch in u'0123456789': + increment = int(ch) + if increment == 0: + raise ScannerError("while scanning a block scalar", start_mark, + "expected indentation indicator in the range 1-9, but found 0", + self.get_mark()) + self.forward() + elif ch in u'0123456789': + increment = int(ch) + if increment == 0: + raise ScannerError("while scanning a block scalar", start_mark, + "expected indentation indicator in the range 1-9, but found 0", + self.get_mark()) + self.forward() + ch = self.peek() + if ch in u'+-': + if ch == '+': + chomping = True + else: + chomping = False + self.forward() + ch = self.peek() + if ch not in u'\0 \r\n\x85\u2028\u2029': + raise ScannerError("while scanning a block scalar", start_mark, + "expected chomping or indentation indicators, but found %r" + % ch.encode('utf-8'), self.get_mark()) + return chomping, increment + + def scan_block_scalar_ignored_line(self, start_mark): + # See the specification for details. + while self.peek() == u' ': + self.forward() + if self.peek() == u'#': + while self.peek() not in u'\0\r\n\x85\u2028\u2029': + self.forward() + ch = self.peek() + if ch not in u'\0\r\n\x85\u2028\u2029': + raise ScannerError("while scanning a block scalar", start_mark, + "expected a comment or a line break, but found %r" + % ch.encode('utf-8'), self.get_mark()) + self.scan_line_break() + + def scan_block_scalar_indentation(self): + # See the specification for details. + chunks = [] + max_indent = 0 + end_mark = self.get_mark() + while self.peek() in u' \r\n\x85\u2028\u2029': + if self.peek() != u' ': + chunks.append(self.scan_line_break()) + end_mark = self.get_mark() + else: + self.forward() + if self.column > max_indent: + max_indent = self.column + return chunks, max_indent, end_mark + + def scan_block_scalar_breaks(self, indent): + # See the specification for details. + chunks = [] + end_mark = self.get_mark() + while self.column < indent and self.peek() == u' ': + self.forward() + while self.peek() in u'\r\n\x85\u2028\u2029': + chunks.append(self.scan_line_break()) + end_mark = self.get_mark() + while self.column < indent and self.peek() == u' ': + self.forward() + return chunks, end_mark + + def scan_flow_scalar(self, style): + # See the specification for details. + # Note that we loose indentation rules for quoted scalars. Quoted + # scalars don't need to adhere indentation because " and ' clearly + # mark the beginning and the end of them. Therefore we are less + # restrictive then the specification requires. We only need to check + # that document separators are not included in scalars. + if style == '"': + double = True + else: + double = False + chunks = [] + start_mark = self.get_mark() + quote = self.peek() + self.forward() + chunks.extend(self.scan_flow_scalar_non_spaces(double, start_mark)) + while self.peek() != quote: + chunks.extend(self.scan_flow_scalar_spaces(double, start_mark)) + chunks.extend(self.scan_flow_scalar_non_spaces(double, start_mark)) + self.forward() + end_mark = self.get_mark() + return ScalarToken(u''.join(chunks), False, start_mark, end_mark, + style) + + ESCAPE_REPLACEMENTS = { + u'0': u'\0', + u'a': u'\x07', + u'b': u'\x08', + u't': u'\x09', + u'\t': u'\x09', + u'n': u'\x0A', + u'v': u'\x0B', + u'f': u'\x0C', + u'r': u'\x0D', + u'e': u'\x1B', + u' ': u'\x20', + u'\"': u'\"', + u'\\': u'\\', + u'/': u'/', + u'N': u'\x85', + u'_': u'\xA0', + u'L': u'\u2028', + u'P': u'\u2029', + } + + ESCAPE_CODES = { + u'x': 2, + u'u': 4, + u'U': 8, + } + + def scan_flow_scalar_non_spaces(self, double, start_mark): + # See the specification for details. + chunks = [] + while True: + length = 0 + while self.peek(length) not in u'\'\"\\\0 \t\r\n\x85\u2028\u2029': + length += 1 + if length: + chunks.append(self.prefix(length)) + self.forward(length) + ch = self.peek() + if not double and ch == u'\'' and self.peek(1) == u'\'': + chunks.append(u'\'') + self.forward(2) + elif (double and ch == u'\'') or (not double and ch in u'\"\\'): + chunks.append(ch) + self.forward() + elif double and ch == u'\\': + self.forward() + ch = self.peek() + if ch in self.ESCAPE_REPLACEMENTS: + chunks.append(self.ESCAPE_REPLACEMENTS[ch]) + self.forward() + elif ch in self.ESCAPE_CODES: + length = self.ESCAPE_CODES[ch] + self.forward() + for k in range(length): + if self.peek(k) not in u'0123456789ABCDEFabcdef': + raise ScannerError("while scanning a double-quoted scalar", start_mark, + "expected escape sequence of %d hexdecimal numbers, but found %r" % + (length, self.peek(k).encode('utf-8')), self.get_mark()) + code = int(self.prefix(length), 16) + chunks.append(unichr(code)) + self.forward(length) + elif ch in u'\r\n\x85\u2028\u2029': + self.scan_line_break() + chunks.extend(self.scan_flow_scalar_breaks(double, start_mark)) + else: + raise ScannerError("while scanning a double-quoted scalar", start_mark, + "found unknown escape character %r" % ch.encode('utf-8'), self.get_mark()) + else: + return chunks + + def scan_flow_scalar_spaces(self, double, start_mark): + # See the specification for details. + chunks = [] + length = 0 + while self.peek(length) in u' \t': + length += 1 + whitespaces = self.prefix(length) + self.forward(length) + ch = self.peek() + if ch == u'\0': + raise ScannerError("while scanning a quoted scalar", start_mark, + "found unexpected end of stream", self.get_mark()) + elif ch in u'\r\n\x85\u2028\u2029': + line_break = self.scan_line_break() + breaks = self.scan_flow_scalar_breaks(double, start_mark) + if line_break != u'\n': + chunks.append(line_break) + elif not breaks: + chunks.append(u' ') + chunks.extend(breaks) + else: + chunks.append(whitespaces) + return chunks + + def scan_flow_scalar_breaks(self, double, start_mark): + # See the specification for details. + chunks = [] + while True: + # Instead of checking indentation, we check for document + # separators. + prefix = self.prefix(3) + if (prefix == u'---' or prefix == u'...') \ + and self.peek(3) in u'\0 \t\r\n\x85\u2028\u2029': + raise ScannerError("while scanning a quoted scalar", start_mark, + "found unexpected document separator", self.get_mark()) + while self.peek() in u' \t': + self.forward() + if self.peek() in u'\r\n\x85\u2028\u2029': + chunks.append(self.scan_line_break()) + else: + return chunks + + def scan_plain(self): + # See the specification for details. + # We add an additional restriction for the flow context: + # plain scalars in the flow context cannot contain ',' or '?'. + # We also keep track of the `allow_simple_key` flag here. + # Indentation rules are loosed for the flow context. + chunks = [] + start_mark = self.get_mark() + end_mark = start_mark + indent = self.indent+1 + # We allow zero indentation for scalars, but then we need to check for + # document separators at the beginning of the line. + #if indent == 0: + # indent = 1 + spaces = [] + while True: + length = 0 + if self.peek() == u'#': + break + while True: + ch = self.peek(length) + if ch in u'\0 \t\r\n\x85\u2028\u2029' \ + or (ch == u':' and + self.peek(length+1) in u'\0 \t\r\n\x85\u2028\u2029' + + (u',[]{}' if self.flow_level else u''))\ + or (self.flow_level and ch in u',?[]{}'): + break + length += 1 + if length == 0: + break + self.allow_simple_key = False + chunks.extend(spaces) + chunks.append(self.prefix(length)) + self.forward(length) + end_mark = self.get_mark() + spaces = self.scan_plain_spaces(indent, start_mark) + if not spaces or self.peek() == u'#' \ + or (not self.flow_level and self.column < indent): + break + return ScalarToken(u''.join(chunks), True, start_mark, end_mark) + + def scan_plain_spaces(self, indent, start_mark): + # See the specification for details. + # The specification is really confusing about tabs in plain scalars. + # We just forbid them completely. Do not use tabs in YAML! + chunks = [] + length = 0 + while self.peek(length) in u' ': + length += 1 + whitespaces = self.prefix(length) + self.forward(length) + ch = self.peek() + if ch in u'\r\n\x85\u2028\u2029': + line_break = self.scan_line_break() + self.allow_simple_key = True + prefix = self.prefix(3) + if (prefix == u'---' or prefix == u'...') \ + and self.peek(3) in u'\0 \t\r\n\x85\u2028\u2029': + return + breaks = [] + while self.peek() in u' \r\n\x85\u2028\u2029': + if self.peek() == ' ': + self.forward() + else: + breaks.append(self.scan_line_break()) + prefix = self.prefix(3) + if (prefix == u'---' or prefix == u'...') \ + and self.peek(3) in u'\0 \t\r\n\x85\u2028\u2029': + return + if line_break != u'\n': + chunks.append(line_break) + elif not breaks: + chunks.append(u' ') + chunks.extend(breaks) + elif whitespaces: + chunks.append(whitespaces) + return chunks + + def scan_tag_handle(self, name, start_mark): + # See the specification for details. + # For some strange reasons, the specification does not allow '_' in + # tag handles. I have allowed it anyway. + ch = self.peek() + if ch != u'!': + raise ScannerError("while scanning a %s" % name, start_mark, + "expected '!', but found %r" % ch.encode('utf-8'), + self.get_mark()) + length = 1 + ch = self.peek(length) + if ch != u' ': + while u'0' <= ch <= u'9' or u'A' <= ch <= u'Z' or u'a' <= ch <= u'z' \ + or ch in u'-_': + length += 1 + ch = self.peek(length) + if ch != u'!': + self.forward(length) + raise ScannerError("while scanning a %s" % name, start_mark, + "expected '!', but found %r" % ch.encode('utf-8'), + self.get_mark()) + length += 1 + value = self.prefix(length) + self.forward(length) + return value + + def scan_tag_uri(self, name, start_mark): + # See the specification for details. + # Note: we do not check if URI is well-formed. + chunks = [] + length = 0 + ch = self.peek(length) + while u'0' <= ch <= u'9' or u'A' <= ch <= u'Z' or u'a' <= ch <= u'z' \ + or ch in u'-;/?:@&=+$,_.!~*\'()[]%': + if ch == u'%': + chunks.append(self.prefix(length)) + self.forward(length) + length = 0 + chunks.append(self.scan_uri_escapes(name, start_mark)) + else: + length += 1 + ch = self.peek(length) + if length: + chunks.append(self.prefix(length)) + self.forward(length) + length = 0 + if not chunks: + raise ScannerError("while parsing a %s" % name, start_mark, + "expected URI, but found %r" % ch.encode('utf-8'), + self.get_mark()) + return u''.join(chunks) + + def scan_uri_escapes(self, name, start_mark): + # See the specification for details. + bytes = [] + mark = self.get_mark() + while self.peek() == u'%': + self.forward() + for k in range(2): + if self.peek(k) not in u'0123456789ABCDEFabcdef': + raise ScannerError("while scanning a %s" % name, start_mark, + "expected URI escape sequence of 2 hexdecimal numbers, but found %r" % + (self.peek(k).encode('utf-8')), self.get_mark()) + bytes.append(chr(int(self.prefix(2), 16))) + self.forward(2) + try: + value = unicode(''.join(bytes), 'utf-8') + except UnicodeDecodeError, exc: + raise ScannerError("while scanning a %s" % name, start_mark, str(exc), mark) + return value + + def scan_line_break(self): + # Transforms: + # '\r\n' : '\n' + # '\r' : '\n' + # '\n' : '\n' + # '\x85' : '\n' + # '\u2028' : '\u2028' + # '\u2029 : '\u2029' + # default : '' + ch = self.peek() + if ch in u'\r\n\x85': + if self.prefix(2) == u'\r\n': + self.forward(2) + else: + self.forward() + return u'\n' + elif ch in u'\u2028\u2029': + self.forward() + return ch + return u'' diff --git a/third_party/python/PyYAML/lib/yaml/serializer.py b/third_party/python/PyYAML/lib/yaml/serializer.py new file mode 100644 index 0000000000..0bf1e96dc1 --- /dev/null +++ b/third_party/python/PyYAML/lib/yaml/serializer.py @@ -0,0 +1,111 @@ + +__all__ = ['Serializer', 'SerializerError'] + +from error import YAMLError +from events import * +from nodes import * + +class SerializerError(YAMLError): + pass + +class Serializer(object): + + ANCHOR_TEMPLATE = u'id%03d' + + def __init__(self, encoding=None, + explicit_start=None, explicit_end=None, version=None, tags=None): + self.use_encoding = encoding + self.use_explicit_start = explicit_start + self.use_explicit_end = explicit_end + self.use_version = version + self.use_tags = tags + self.serialized_nodes = {} + self.anchors = {} + self.last_anchor_id = 0 + self.closed = None + + def open(self): + if self.closed is None: + self.emit(StreamStartEvent(encoding=self.use_encoding)) + self.closed = False + elif self.closed: + raise SerializerError("serializer is closed") + else: + raise SerializerError("serializer is already opened") + + def close(self): + if self.closed is None: + raise SerializerError("serializer is not opened") + elif not self.closed: + self.emit(StreamEndEvent()) + self.closed = True + + #def __del__(self): + # self.close() + + def serialize(self, node): + if self.closed is None: + raise SerializerError("serializer is not opened") + elif self.closed: + raise SerializerError("serializer is closed") + self.emit(DocumentStartEvent(explicit=self.use_explicit_start, + version=self.use_version, tags=self.use_tags)) + self.anchor_node(node) + self.serialize_node(node, None, None) + self.emit(DocumentEndEvent(explicit=self.use_explicit_end)) + self.serialized_nodes = {} + self.anchors = {} + self.last_anchor_id = 0 + + def anchor_node(self, node): + if node in self.anchors: + if self.anchors[node] is None: + self.anchors[node] = self.generate_anchor(node) + else: + self.anchors[node] = None + if isinstance(node, SequenceNode): + for item in node.value: + self.anchor_node(item) + elif isinstance(node, MappingNode): + for key, value in node.value: + self.anchor_node(key) + self.anchor_node(value) + + def generate_anchor(self, node): + self.last_anchor_id += 1 + return self.ANCHOR_TEMPLATE % self.last_anchor_id + + def serialize_node(self, node, parent, index): + alias = self.anchors[node] + if node in self.serialized_nodes: + self.emit(AliasEvent(alias)) + else: + self.serialized_nodes[node] = True + self.descend_resolver(parent, index) + if isinstance(node, ScalarNode): + detected_tag = self.resolve(ScalarNode, node.value, (True, False)) + default_tag = self.resolve(ScalarNode, node.value, (False, True)) + implicit = (node.tag == detected_tag), (node.tag == default_tag) + self.emit(ScalarEvent(alias, node.tag, implicit, node.value, + style=node.style)) + elif isinstance(node, SequenceNode): + implicit = (node.tag + == self.resolve(SequenceNode, node.value, True)) + self.emit(SequenceStartEvent(alias, node.tag, implicit, + flow_style=node.flow_style)) + index = 0 + for item in node.value: + self.serialize_node(item, node, index) + index += 1 + self.emit(SequenceEndEvent()) + elif isinstance(node, MappingNode): + implicit = (node.tag + == self.resolve(MappingNode, node.value, True)) + self.emit(MappingStartEvent(alias, node.tag, implicit, + flow_style=node.flow_style)) + for key, value in node.value: + self.serialize_node(key, node, None) + self.serialize_node(value, node, key) + self.emit(MappingEndEvent()) + self.ascend_resolver() + diff --git a/third_party/python/PyYAML/lib/yaml/tokens.py b/third_party/python/PyYAML/lib/yaml/tokens.py new file mode 100644 index 0000000000..4d0b48a394 --- /dev/null +++ b/third_party/python/PyYAML/lib/yaml/tokens.py @@ -0,0 +1,104 @@ + +class Token(object): + def __init__(self, start_mark, end_mark): + self.start_mark = start_mark + self.end_mark = end_mark + def __repr__(self): + attributes = [key for key in self.__dict__ + if not key.endswith('_mark')] + attributes.sort() + arguments = ', '.join(['%s=%r' % (key, getattr(self, key)) + for key in attributes]) + return '%s(%s)' % (self.__class__.__name__, arguments) + +#class BOMToken(Token): +# id = '' + +class DirectiveToken(Token): + id = '' + def __init__(self, name, value, start_mark, end_mark): + self.name = name + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + +class DocumentStartToken(Token): + id = '' + +class DocumentEndToken(Token): + id = '' + +class StreamStartToken(Token): + id = '' + def __init__(self, start_mark=None, end_mark=None, + encoding=None): + self.start_mark = start_mark + self.end_mark = end_mark + self.encoding = encoding + +class StreamEndToken(Token): + id = '' + +class BlockSequenceStartToken(Token): + id = '' + +class BlockMappingStartToken(Token): + id = '' + +class BlockEndToken(Token): + id = '' + +class FlowSequenceStartToken(Token): + id = '[' + +class FlowMappingStartToken(Token): + id = '{' + +class FlowSequenceEndToken(Token): + id = ']' + +class FlowMappingEndToken(Token): + id = '}' + +class KeyToken(Token): + id = '?' + +class ValueToken(Token): + id = ':' + +class BlockEntryToken(Token): + id = '-' + +class FlowEntryToken(Token): + id = ',' + +class AliasToken(Token): + id = '' + def __init__(self, value, start_mark, end_mark): + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + +class AnchorToken(Token): + id = '' + def __init__(self, value, start_mark, end_mark): + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + +class TagToken(Token): + id = '' + def __init__(self, value, start_mark, end_mark): + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + +class ScalarToken(Token): + id = '' + def __init__(self, value, plain, start_mark, end_mark, style=None): + self.value = value + self.plain = plain + self.start_mark = start_mark + self.end_mark = end_mark + self.style = style + diff --git a/third_party/python/PyYAML/lib3/PyYAML.egg-info/PKG-INFO b/third_party/python/PyYAML/lib3/PyYAML.egg-info/PKG-INFO new file mode 100644 index 0000000000..04d0abf6e5 --- /dev/null +++ b/third_party/python/PyYAML/lib3/PyYAML.egg-info/PKG-INFO @@ -0,0 +1,44 @@ +Metadata-Version: 1.2 +Name: PyYAML +Version: 5.4.1 +Summary: YAML parser and emitter for Python +Home-page: https://pyyaml.org/ +Author: Kirill Simonov +Author-email: xi@resolvent.net +License: MIT +Download-URL: https://pypi.org/project/PyYAML/ +Project-URL: Bug Tracker, https://github.com/yaml/pyyaml/issues +Project-URL: CI, https://github.com/yaml/pyyaml/actions +Project-URL: Documentation, https://pyyaml.org/wiki/PyYAMLDocumentation +Project-URL: Mailing lists, http://lists.sourceforge.net/lists/listinfo/yaml-core +Project-URL: Source Code, https://github.com/yaml/pyyaml +Description: YAML is a data serialization format designed for human readability + and interaction with scripting languages. PyYAML is a YAML parser + and emitter for Python. + + PyYAML features a complete YAML 1.1 parser, Unicode support, pickle + support, capable extension API, and sensible error messages. PyYAML + supports standard YAML tags and provides Python-specific tags that + allow to represent an arbitrary Python object. + + PyYAML is applicable for a broad range of tasks from complex + configuration files to object serialization and persistence. +Platform: Any +Classifier: Development Status :: 5 - Production/Stable +Classifier: Intended Audience :: Developers +Classifier: License :: OSI Approved :: MIT License +Classifier: Operating System :: OS Independent +Classifier: Programming Language :: Cython +Classifier: Programming Language :: Python +Classifier: Programming Language :: Python :: 2 +Classifier: Programming Language :: Python :: 2.7 +Classifier: Programming Language :: Python :: 3 +Classifier: Programming Language :: Python :: 3.6 +Classifier: Programming Language :: Python :: 3.7 +Classifier: Programming Language :: Python :: 3.8 +Classifier: Programming Language :: Python :: 3.9 +Classifier: Programming Language :: Python :: Implementation :: CPython +Classifier: Programming Language :: Python :: Implementation :: PyPy +Classifier: Topic :: Software Development :: Libraries :: Python Modules +Classifier: Topic :: Text Processing :: Markup +Requires-Python: >=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.* diff --git a/third_party/python/PyYAML/lib3/PyYAML.egg-info/SOURCES.txt b/third_party/python/PyYAML/lib3/PyYAML.egg-info/SOURCES.txt new file mode 100644 index 0000000000..89f5a63c09 --- /dev/null +++ b/third_party/python/PyYAML/lib3/PyYAML.egg-info/SOURCES.txt @@ -0,0 +1,670 @@ +CHANGES +LICENSE +MANIFEST.in +Makefile +README +pyproject.toml +setup.cfg +setup.py +examples/pygments-lexer/example.yaml +examples/pygments-lexer/yaml.py +examples/yaml-highlight/yaml_hl.cfg +examples/yaml-highlight/yaml_hl.py +lib/_yaml/__init__.py +lib/yaml/__init__.py +lib/yaml/composer.py +lib/yaml/constructor.py +lib/yaml/cyaml.py +lib/yaml/dumper.py +lib/yaml/emitter.py +lib/yaml/error.py +lib/yaml/events.py +lib/yaml/loader.py +lib/yaml/nodes.py +lib/yaml/parser.py +lib/yaml/reader.py +lib/yaml/representer.py +lib/yaml/resolver.py +lib/yaml/scanner.py +lib/yaml/serializer.py +lib/yaml/tokens.py +lib3/PyYAML.egg-info/PKG-INFO +lib3/PyYAML.egg-info/SOURCES.txt +lib3/PyYAML.egg-info/dependency_links.txt +lib3/PyYAML.egg-info/top_level.txt +lib3/_yaml/__init__.py +lib3/yaml/__init__.py +lib3/yaml/composer.py +lib3/yaml/constructor.py +lib3/yaml/cyaml.py +lib3/yaml/dumper.py +lib3/yaml/emitter.py +lib3/yaml/error.py +lib3/yaml/events.py +lib3/yaml/loader.py +lib3/yaml/nodes.py +lib3/yaml/parser.py +lib3/yaml/reader.py +lib3/yaml/representer.py +lib3/yaml/resolver.py +lib3/yaml/scanner.py +lib3/yaml/serializer.py +lib3/yaml/tokens.py +tests/data/a-nasty-libyaml-bug.loader-error +tests/data/aliases-cdumper-bug.code +tests/data/aliases.events +tests/data/bool.data +tests/data/bool.detect +tests/data/construct-binary-py2.code +tests/data/construct-binary-py2.data +tests/data/construct-binary-py3.code +tests/data/construct-binary-py3.data +tests/data/construct-bool.code +tests/data/construct-bool.data +tests/data/construct-custom.code +tests/data/construct-custom.data +tests/data/construct-float.code +tests/data/construct-float.data +tests/data/construct-int.code +tests/data/construct-int.data +tests/data/construct-map.code +tests/data/construct-map.data +tests/data/construct-merge.code +tests/data/construct-merge.data +tests/data/construct-null.code +tests/data/construct-null.data +tests/data/construct-omap.code +tests/data/construct-omap.data +tests/data/construct-pairs.code +tests/data/construct-pairs.data +tests/data/construct-python-bool.code +tests/data/construct-python-bool.data +tests/data/construct-python-bytes-py3.code +tests/data/construct-python-bytes-py3.data +tests/data/construct-python-complex.code +tests/data/construct-python-complex.data +tests/data/construct-python-float.code +tests/data/construct-python-float.data +tests/data/construct-python-int.code +tests/data/construct-python-int.data +tests/data/construct-python-long-short-py2.code +tests/data/construct-python-long-short-py2.data +tests/data/construct-python-long-short-py3.code +tests/data/construct-python-long-short-py3.data +tests/data/construct-python-name-module.code +tests/data/construct-python-name-module.data +tests/data/construct-python-none.code +tests/data/construct-python-none.data +tests/data/construct-python-object.code +tests/data/construct-python-object.data +tests/data/construct-python-str-ascii.code +tests/data/construct-python-str-ascii.data +tests/data/construct-python-str-utf8-py2.code +tests/data/construct-python-str-utf8-py2.data +tests/data/construct-python-str-utf8-py3.code +tests/data/construct-python-str-utf8-py3.data +tests/data/construct-python-tuple-list-dict.code +tests/data/construct-python-tuple-list-dict.data +tests/data/construct-python-unicode-ascii-py2.code +tests/data/construct-python-unicode-ascii-py2.data +tests/data/construct-python-unicode-ascii-py3.code +tests/data/construct-python-unicode-ascii-py3.data +tests/data/construct-python-unicode-utf8-py2.code +tests/data/construct-python-unicode-utf8-py2.data +tests/data/construct-python-unicode-utf8-py3.code +tests/data/construct-python-unicode-utf8-py3.data +tests/data/construct-seq.code +tests/data/construct-seq.data +tests/data/construct-set.code +tests/data/construct-set.data +tests/data/construct-str-ascii.code +tests/data/construct-str-ascii.data +tests/data/construct-str-utf8-py2.code +tests/data/construct-str-utf8-py2.data +tests/data/construct-str-utf8-py3.code +tests/data/construct-str-utf8-py3.data +tests/data/construct-str.code +tests/data/construct-str.data +tests/data/construct-timestamp.code +tests/data/construct-timestamp.data +tests/data/construct-value.code +tests/data/construct-value.data +tests/data/document-separator-in-quoted-scalar.loader-error +tests/data/documents.events +tests/data/duplicate-anchor-1.loader-error +tests/data/duplicate-anchor-2.loader-error +tests/data/duplicate-key.former-loader-error.code +tests/data/duplicate-key.former-loader-error.data +tests/data/duplicate-mapping-key.former-loader-error.code +tests/data/duplicate-mapping-key.former-loader-error.data +tests/data/duplicate-merge-key.former-loader-error.code +tests/data/duplicate-merge-key.former-loader-error.data +tests/data/duplicate-tag-directive.loader-error +tests/data/duplicate-value-key.former-loader-error.code +tests/data/duplicate-value-key.former-loader-error.data +tests/data/duplicate-yaml-directive.loader-error +tests/data/emit-block-scalar-in-simple-key-context-bug.canonical +tests/data/emit-block-scalar-in-simple-key-context-bug.data +tests/data/emitting-unacceptable-unicode-character-bug-py3.code +tests/data/emitting-unacceptable-unicode-character-bug-py3.data +tests/data/emitting-unacceptable-unicode-character-bug-py3.skip-ext +tests/data/emitting-unacceptable-unicode-character-bug.code +tests/data/emitting-unacceptable-unicode-character-bug.data +tests/data/emitting-unacceptable-unicode-character-bug.skip-ext +tests/data/emoticons.unicode +tests/data/emoticons2.unicode +tests/data/empty-anchor.emitter-error +tests/data/empty-document-bug.canonical +tests/data/empty-document-bug.data +tests/data/empty-document-bug.empty +tests/data/empty-documents.single-loader-error +tests/data/empty-python-module.loader-error +tests/data/empty-python-name.loader-error +tests/data/empty-tag-handle.emitter-error +tests/data/empty-tag-prefix.emitter-error +tests/data/empty-tag.emitter-error +tests/data/expected-document-end.emitter-error +tests/data/expected-document-start.emitter-error +tests/data/expected-mapping.loader-error +tests/data/expected-node-1.emitter-error +tests/data/expected-node-2.emitter-error +tests/data/expected-nothing.emitter-error +tests/data/expected-scalar.loader-error +tests/data/expected-sequence.loader-error +tests/data/expected-stream-start.emitter-error +tests/data/explicit-document.single-loader-error +tests/data/fetch-complex-value-bug.loader-error +tests/data/float-representer-2.3-bug.code +tests/data/float-representer-2.3-bug.data +tests/data/float.data +tests/data/float.detect +tests/data/forbidden-entry.loader-error +tests/data/forbidden-key.loader-error +tests/data/forbidden-value.loader-error +tests/data/implicit-document.single-loader-error +tests/data/int.data +tests/data/int.detect +tests/data/invalid-anchor-1.loader-error +tests/data/invalid-anchor-2.loader-error +tests/data/invalid-anchor.emitter-error +tests/data/invalid-base64-data-2.loader-error +tests/data/invalid-base64-data.loader-error +tests/data/invalid-block-scalar-indicator.loader-error +tests/data/invalid-character.loader-error +tests/data/invalid-character.stream-error +tests/data/invalid-directive-line.loader-error +tests/data/invalid-directive-name-1.loader-error +tests/data/invalid-directive-name-2.loader-error +tests/data/invalid-escape-character.loader-error +tests/data/invalid-escape-numbers.loader-error +tests/data/invalid-indentation-indicator-1.loader-error +tests/data/invalid-indentation-indicator-2.loader-error +tests/data/invalid-item-without-trailing-break.loader-error +tests/data/invalid-merge-1.loader-error +tests/data/invalid-merge-2.loader-error +tests/data/invalid-omap-1.loader-error +tests/data/invalid-omap-2.loader-error +tests/data/invalid-omap-3.loader-error +tests/data/invalid-pairs-1.loader-error +tests/data/invalid-pairs-2.loader-error +tests/data/invalid-pairs-3.loader-error +tests/data/invalid-python-bytes-2-py3.loader-error +tests/data/invalid-python-bytes-py3.loader-error +tests/data/invalid-python-module-kind.loader-error +tests/data/invalid-python-module-value.loader-error +tests/data/invalid-python-module.loader-error +tests/data/invalid-python-name-kind.loader-error +tests/data/invalid-python-name-module.loader-error +tests/data/invalid-python-name-object.loader-error +tests/data/invalid-python-name-value.loader-error +tests/data/invalid-simple-key.loader-error +tests/data/invalid-single-quote-bug.code +tests/data/invalid-single-quote-bug.data +tests/data/invalid-starting-character.loader-error +tests/data/invalid-tag-1.loader-error +tests/data/invalid-tag-2.loader-error +tests/data/invalid-tag-directive-handle.loader-error +tests/data/invalid-tag-directive-prefix.loader-error +tests/data/invalid-tag-handle-1.emitter-error +tests/data/invalid-tag-handle-1.loader-error +tests/data/invalid-tag-handle-2.emitter-error +tests/data/invalid-tag-handle-2.loader-error +tests/data/invalid-uri-escapes-1.loader-error +tests/data/invalid-uri-escapes-2.loader-error +tests/data/invalid-uri-escapes-3.loader-error +tests/data/invalid-uri.loader-error +tests/data/invalid-utf8-byte.loader-error +tests/data/invalid-utf8-byte.stream-error +tests/data/invalid-yaml-directive-version-1.loader-error +tests/data/invalid-yaml-directive-version-2.loader-error +tests/data/invalid-yaml-directive-version-3.loader-error +tests/data/invalid-yaml-directive-version-4.loader-error +tests/data/invalid-yaml-directive-version-5.loader-error +tests/data/invalid-yaml-directive-version-6.loader-error +tests/data/invalid-yaml-version.loader-error +tests/data/latin.unicode +tests/data/mapping.sort +tests/data/mapping.sorted +tests/data/mappings.events +tests/data/merge.data +tests/data/merge.detect +tests/data/more-floats.code +tests/data/more-floats.data +tests/data/multi-constructor.code +tests/data/multi-constructor.multi +tests/data/myfullloader.subclass_blacklist +tests/data/negative-float-bug.code +tests/data/negative-float-bug.data +tests/data/no-alias-anchor.emitter-error +tests/data/no-alias-anchor.skip-ext +tests/data/no-block-collection-end.loader-error +tests/data/no-block-mapping-end-2.loader-error +tests/data/no-block-mapping-end.loader-error +tests/data/no-document-start.loader-error +tests/data/no-flow-mapping-end.loader-error +tests/data/no-flow-sequence-end.loader-error +tests/data/no-node-1.loader-error +tests/data/no-node-2.loader-error +tests/data/no-tag.emitter-error +tests/data/null.data +tests/data/null.detect +tests/data/odd-utf16.stream-error +tests/data/overwrite-state-new-constructor.loader-error +tests/data/recursive-anchor.former-loader-error +tests/data/recursive-dict.recursive +tests/data/recursive-list.recursive +tests/data/recursive-set.recursive +tests/data/recursive-state.recursive +tests/data/recursive-tuple.recursive +tests/data/recursive.former-dumper-error +tests/data/remove-possible-simple-key-bug.loader-error +tests/data/resolver.data +tests/data/resolver.path +tests/data/run-parser-crash-bug.data +tests/data/scalars.events +tests/data/scan-document-end-bug.canonical +tests/data/scan-document-end-bug.data +tests/data/scan-line-break-bug.canonical +tests/data/scan-line-break-bug.data +tests/data/sequences.events +tests/data/serializer-is-already-opened.dumper-error +tests/data/serializer-is-closed-1.dumper-error +tests/data/serializer-is-closed-2.dumper-error +tests/data/serializer-is-not-opened-1.dumper-error +tests/data/serializer-is-not-opened-2.dumper-error +tests/data/single-dot-is-not-float-bug.code +tests/data/single-dot-is-not-float-bug.data +tests/data/sloppy-indentation.canonical +tests/data/sloppy-indentation.data +tests/data/spec-02-01.data +tests/data/spec-02-01.structure +tests/data/spec-02-01.tokens +tests/data/spec-02-02.data +tests/data/spec-02-02.structure +tests/data/spec-02-02.tokens +tests/data/spec-02-03.data +tests/data/spec-02-03.structure +tests/data/spec-02-03.tokens +tests/data/spec-02-04.data +tests/data/spec-02-04.structure +tests/data/spec-02-04.tokens +tests/data/spec-02-05.data +tests/data/spec-02-05.structure +tests/data/spec-02-05.tokens +tests/data/spec-02-06.data +tests/data/spec-02-06.structure +tests/data/spec-02-06.tokens +tests/data/spec-02-07.data +tests/data/spec-02-07.structure +tests/data/spec-02-07.tokens +tests/data/spec-02-08.data +tests/data/spec-02-08.structure +tests/data/spec-02-08.tokens +tests/data/spec-02-09.data +tests/data/spec-02-09.structure +tests/data/spec-02-09.tokens +tests/data/spec-02-10.data +tests/data/spec-02-10.structure +tests/data/spec-02-10.tokens +tests/data/spec-02-11.data +tests/data/spec-02-11.structure +tests/data/spec-02-11.tokens +tests/data/spec-02-12.data +tests/data/spec-02-12.structure +tests/data/spec-02-12.tokens +tests/data/spec-02-13.data +tests/data/spec-02-13.structure +tests/data/spec-02-13.tokens +tests/data/spec-02-14.data +tests/data/spec-02-14.structure +tests/data/spec-02-14.tokens +tests/data/spec-02-15.data +tests/data/spec-02-15.structure +tests/data/spec-02-15.tokens +tests/data/spec-02-16.data +tests/data/spec-02-16.structure +tests/data/spec-02-16.tokens +tests/data/spec-02-17.data +tests/data/spec-02-17.structure +tests/data/spec-02-17.tokens +tests/data/spec-02-18.data +tests/data/spec-02-18.structure +tests/data/spec-02-18.tokens +tests/data/spec-02-19.data +tests/data/spec-02-19.structure +tests/data/spec-02-19.tokens +tests/data/spec-02-20.data +tests/data/spec-02-20.structure +tests/data/spec-02-20.tokens +tests/data/spec-02-21.data +tests/data/spec-02-21.structure +tests/data/spec-02-21.tokens +tests/data/spec-02-22.data +tests/data/spec-02-22.structure +tests/data/spec-02-22.tokens +tests/data/spec-02-23.data +tests/data/spec-02-23.structure +tests/data/spec-02-23.tokens +tests/data/spec-02-24.data +tests/data/spec-02-24.structure +tests/data/spec-02-24.tokens +tests/data/spec-02-25.data +tests/data/spec-02-25.structure +tests/data/spec-02-25.tokens +tests/data/spec-02-26.data +tests/data/spec-02-26.structure +tests/data/spec-02-26.tokens +tests/data/spec-02-27.data +tests/data/spec-02-27.structure +tests/data/spec-02-27.tokens +tests/data/spec-02-28.data +tests/data/spec-02-28.structure +tests/data/spec-02-28.tokens +tests/data/spec-05-01-utf16be.data +tests/data/spec-05-01-utf16be.empty +tests/data/spec-05-01-utf16le.data +tests/data/spec-05-01-utf16le.empty +tests/data/spec-05-01-utf8.data +tests/data/spec-05-01-utf8.empty +tests/data/spec-05-02-utf16be.data +tests/data/spec-05-02-utf16be.error +tests/data/spec-05-02-utf16le.data +tests/data/spec-05-02-utf16le.error +tests/data/spec-05-02-utf8.data +tests/data/spec-05-02-utf8.error +tests/data/spec-05-03.canonical +tests/data/spec-05-03.data +tests/data/spec-05-04.canonical +tests/data/spec-05-04.data +tests/data/spec-05-05.data +tests/data/spec-05-05.empty +tests/data/spec-05-06.canonical +tests/data/spec-05-06.data +tests/data/spec-05-07.canonical +tests/data/spec-05-07.data +tests/data/spec-05-08.canonical +tests/data/spec-05-08.data +tests/data/spec-05-09.canonical +tests/data/spec-05-09.data +tests/data/spec-05-10.data +tests/data/spec-05-10.error +tests/data/spec-05-11.canonical +tests/data/spec-05-11.data +tests/data/spec-05-12.data +tests/data/spec-05-12.error +tests/data/spec-05-13.canonical +tests/data/spec-05-13.data +tests/data/spec-05-14.canonical +tests/data/spec-05-14.data +tests/data/spec-05-15.data +tests/data/spec-05-15.error +tests/data/spec-06-01.canonical +tests/data/spec-06-01.data +tests/data/spec-06-02.data +tests/data/spec-06-02.empty +tests/data/spec-06-03.canonical +tests/data/spec-06-03.data +tests/data/spec-06-04.canonical +tests/data/spec-06-04.data +tests/data/spec-06-05.canonical +tests/data/spec-06-05.data +tests/data/spec-06-06.canonical +tests/data/spec-06-06.data +tests/data/spec-06-07.canonical +tests/data/spec-06-07.data +tests/data/spec-06-08.canonical +tests/data/spec-06-08.data +tests/data/spec-07-01.canonical +tests/data/spec-07-01.data +tests/data/spec-07-01.skip-ext +tests/data/spec-07-02.canonical +tests/data/spec-07-02.data +tests/data/spec-07-02.skip-ext +tests/data/spec-07-03.data +tests/data/spec-07-03.error +tests/data/spec-07-04.canonical +tests/data/spec-07-04.data +tests/data/spec-07-05.data +tests/data/spec-07-05.error +tests/data/spec-07-06.canonical +tests/data/spec-07-06.data +tests/data/spec-07-07a.canonical +tests/data/spec-07-07a.data +tests/data/spec-07-07b.canonical +tests/data/spec-07-07b.data +tests/data/spec-07-08.canonical +tests/data/spec-07-08.data +tests/data/spec-07-09.canonical +tests/data/spec-07-09.data +tests/data/spec-07-10.canonical +tests/data/spec-07-10.data +tests/data/spec-07-11.data +tests/data/spec-07-11.empty +tests/data/spec-07-12a.canonical +tests/data/spec-07-12a.data +tests/data/spec-07-12b.canonical +tests/data/spec-07-12b.data +tests/data/spec-07-13.canonical +tests/data/spec-07-13.data +tests/data/spec-08-01.canonical +tests/data/spec-08-01.data +tests/data/spec-08-02.canonical +tests/data/spec-08-02.data +tests/data/spec-08-03.canonical +tests/data/spec-08-03.data +tests/data/spec-08-04.data +tests/data/spec-08-04.error +tests/data/spec-08-05.canonical +tests/data/spec-08-05.data +tests/data/spec-08-06.data +tests/data/spec-08-06.error +tests/data/spec-08-07.canonical +tests/data/spec-08-07.data +tests/data/spec-08-08.canonical +tests/data/spec-08-08.data +tests/data/spec-08-09.canonical +tests/data/spec-08-09.data +tests/data/spec-08-10.canonical +tests/data/spec-08-10.data +tests/data/spec-08-11.canonical +tests/data/spec-08-11.data +tests/data/spec-08-12.canonical +tests/data/spec-08-12.data +tests/data/spec-08-13.canonical +tests/data/spec-08-13.data +tests/data/spec-08-13.skip-ext +tests/data/spec-08-14.canonical +tests/data/spec-08-14.data +tests/data/spec-08-15.canonical +tests/data/spec-08-15.data +tests/data/spec-09-01.canonical +tests/data/spec-09-01.data +tests/data/spec-09-02.canonical +tests/data/spec-09-02.data +tests/data/spec-09-03.canonical +tests/data/spec-09-03.data +tests/data/spec-09-04.canonical +tests/data/spec-09-04.data +tests/data/spec-09-05.canonical +tests/data/spec-09-05.data +tests/data/spec-09-06.canonical +tests/data/spec-09-06.data +tests/data/spec-09-07.canonical +tests/data/spec-09-07.data +tests/data/spec-09-08.canonical +tests/data/spec-09-08.data +tests/data/spec-09-09.canonical +tests/data/spec-09-09.data +tests/data/spec-09-10.canonical +tests/data/spec-09-10.data +tests/data/spec-09-11.canonical +tests/data/spec-09-11.data +tests/data/spec-09-12.canonical +tests/data/spec-09-12.data +tests/data/spec-09-13.canonical +tests/data/spec-09-13.data +tests/data/spec-09-14.data +tests/data/spec-09-14.error +tests/data/spec-09-15.canonical +tests/data/spec-09-15.data +tests/data/spec-09-16.canonical +tests/data/spec-09-16.data +tests/data/spec-09-17.canonical +tests/data/spec-09-17.data +tests/data/spec-09-18.canonical +tests/data/spec-09-18.data +tests/data/spec-09-19.canonical +tests/data/spec-09-19.data +tests/data/spec-09-20.canonical +tests/data/spec-09-20.data +tests/data/spec-09-20.skip-ext +tests/data/spec-09-21.data +tests/data/spec-09-21.error +tests/data/spec-09-22.canonical +tests/data/spec-09-22.data +tests/data/spec-09-23.canonical +tests/data/spec-09-23.data +tests/data/spec-09-24.canonical +tests/data/spec-09-24.data +tests/data/spec-09-25.canonical +tests/data/spec-09-25.data +tests/data/spec-09-26.canonical +tests/data/spec-09-26.data +tests/data/spec-09-27.canonical +tests/data/spec-09-27.data +tests/data/spec-09-28.canonical +tests/data/spec-09-28.data +tests/data/spec-09-29.canonical +tests/data/spec-09-29.data +tests/data/spec-09-30.canonical +tests/data/spec-09-30.data +tests/data/spec-09-31.canonical +tests/data/spec-09-31.data +tests/data/spec-09-32.canonical +tests/data/spec-09-32.data +tests/data/spec-09-33.canonical +tests/data/spec-09-33.data +tests/data/spec-10-01.canonical +tests/data/spec-10-01.data +tests/data/spec-10-02.canonical +tests/data/spec-10-02.data +tests/data/spec-10-03.canonical +tests/data/spec-10-03.data +tests/data/spec-10-04.canonical +tests/data/spec-10-04.data +tests/data/spec-10-05.canonical +tests/data/spec-10-05.data +tests/data/spec-10-06.canonical +tests/data/spec-10-06.data +tests/data/spec-10-07.canonical +tests/data/spec-10-07.data +tests/data/spec-10-08.data +tests/data/spec-10-08.error +tests/data/spec-10-09.canonical +tests/data/spec-10-09.data +tests/data/spec-10-10.canonical +tests/data/spec-10-10.data +tests/data/spec-10-11.canonical +tests/data/spec-10-11.data +tests/data/spec-10-12.canonical +tests/data/spec-10-12.data +tests/data/spec-10-13.canonical +tests/data/spec-10-13.data +tests/data/spec-10-14.canonical +tests/data/spec-10-14.data +tests/data/spec-10-15.canonical +tests/data/spec-10-15.data +tests/data/str.data +tests/data/str.detect +tests/data/tags.events +tests/data/test_mark.marks +tests/data/timestamp-bugs.code +tests/data/timestamp-bugs.data +tests/data/timestamp.data +tests/data/timestamp.detect +tests/data/unacceptable-key.loader-error +tests/data/unclosed-bracket.loader-error +tests/data/unclosed-quoted-scalar.loader-error +tests/data/undefined-anchor.loader-error +tests/data/undefined-constructor.loader-error +tests/data/undefined-tag-handle.loader-error +tests/data/unknown.dumper-error +tests/data/unsupported-version.emitter-error +tests/data/utf16be.code +tests/data/utf16be.data +tests/data/utf16le.code +tests/data/utf16le.data +tests/data/utf8-implicit.code +tests/data/utf8-implicit.data +tests/data/utf8.code +tests/data/utf8.data +tests/data/value.data +tests/data/value.detect +tests/data/yaml.data +tests/data/yaml.detect +tests/lib/canonical.py +tests/lib/test_all.py +tests/lib/test_appliance.py +tests/lib/test_build.py +tests/lib/test_build_ext.py +tests/lib/test_canonical.py +tests/lib/test_constructor.py +tests/lib/test_emitter.py +tests/lib/test_errors.py +tests/lib/test_input_output.py +tests/lib/test_mark.py +tests/lib/test_multi_constructor.py +tests/lib/test_reader.py +tests/lib/test_recursive.py +tests/lib/test_representer.py +tests/lib/test_resolver.py +tests/lib/test_sort_keys.py +tests/lib/test_structure.py +tests/lib/test_tokens.py +tests/lib/test_yaml.py +tests/lib/test_yaml_ext.py +tests/lib3/canonical.py +tests/lib3/test_all.py +tests/lib3/test_appliance.py +tests/lib3/test_build.py +tests/lib3/test_build_ext.py +tests/lib3/test_canonical.py +tests/lib3/test_constructor.py +tests/lib3/test_emitter.py +tests/lib3/test_errors.py +tests/lib3/test_input_output.py +tests/lib3/test_mark.py +tests/lib3/test_multi_constructor.py +tests/lib3/test_reader.py +tests/lib3/test_recursive.py +tests/lib3/test_representer.py +tests/lib3/test_resolver.py +tests/lib3/test_sort_keys.py +tests/lib3/test_structure.py +tests/lib3/test_tokens.py +tests/lib3/test_yaml.py +tests/lib3/test_yaml_ext.py +yaml/__init__.pxd +yaml/_yaml.h +yaml/_yaml.pxd +yaml/_yaml.pyx \ No newline at end of file diff --git a/third_party/python/PyYAML/lib3/PyYAML.egg-info/dependency_links.txt b/third_party/python/PyYAML/lib3/PyYAML.egg-info/dependency_links.txt new file mode 100644 index 0000000000..8b13789179 --- /dev/null +++ b/third_party/python/PyYAML/lib3/PyYAML.egg-info/dependency_links.txt @@ -0,0 +1 @@ + diff --git a/third_party/python/PyYAML/lib3/PyYAML.egg-info/top_level.txt b/third_party/python/PyYAML/lib3/PyYAML.egg-info/top_level.txt new file mode 100644 index 0000000000..e6475e911f --- /dev/null +++ b/third_party/python/PyYAML/lib3/PyYAML.egg-info/top_level.txt @@ -0,0 +1,2 @@ +_yaml +yaml diff --git a/third_party/python/PyYAML/lib3/_yaml/__init__.py b/third_party/python/PyYAML/lib3/_yaml/__init__.py new file mode 100644 index 0000000000..7baa8c4b68 --- /dev/null +++ b/third_party/python/PyYAML/lib3/_yaml/__init__.py @@ -0,0 +1,33 @@ +# This is a stub package designed to roughly emulate the _yaml +# extension module, which previously existed as a standalone module +# and has been moved into the `yaml` package namespace. +# It does not perfectly mimic its old counterpart, but should get +# close enough for anyone who's relying on it even when they shouldn't. +import yaml + +# in some circumstances, the yaml module we imoprted may be from a different version, so we need +# to tread carefully when poking at it here (it may not have the attributes we expect) +if not getattr(yaml, '__with_libyaml__', False): + from sys import version_info + + exc = ModuleNotFoundError if version_info >= (3, 6) else ImportError + raise exc("No module named '_yaml'") +else: + from yaml._yaml import * + import warnings + warnings.warn( + 'The _yaml extension module is now located at yaml._yaml' + ' and its location is subject to change. To use the' + ' LibYAML-based parser and emitter, import from `yaml`:' + ' `from yaml import CLoader as Loader, CDumper as Dumper`.', + DeprecationWarning + ) + del warnings + # Don't `del yaml` here because yaml is actually an existing + # namespace member of _yaml. + +__name__ = '_yaml' +# If the module is top-level (i.e. not a part of any specific package) +# then the attribute should be set to ''. +# https://docs.python.org/3.8/library/types.html +__package__ = '' diff --git a/third_party/python/PyYAML/lib3/yaml/__init__.py b/third_party/python/PyYAML/lib3/yaml/__init__.py new file mode 100644 index 0000000000..86d07b5525 --- /dev/null +++ b/third_party/python/PyYAML/lib3/yaml/__init__.py @@ -0,0 +1,427 @@ + +from .error import * + +from .tokens import * +from .events import * +from .nodes import * + +from .loader import * +from .dumper import * + +__version__ = '5.4.1' +try: + from .cyaml import * + __with_libyaml__ = True +except ImportError: + __with_libyaml__ = False + +import io + +#------------------------------------------------------------------------------ +# Warnings control +#------------------------------------------------------------------------------ + +# 'Global' warnings state: +_warnings_enabled = { + 'YAMLLoadWarning': True, +} + +# Get or set global warnings' state +def warnings(settings=None): + if settings is None: + return _warnings_enabled + + if type(settings) is dict: + for key in settings: + if key in _warnings_enabled: + _warnings_enabled[key] = settings[key] + +# Warn when load() is called without Loader=... +class YAMLLoadWarning(RuntimeWarning): + pass + +def load_warning(method): + if _warnings_enabled['YAMLLoadWarning'] is False: + return + + import warnings + + message = ( + "calling yaml.%s() without Loader=... is deprecated, as the " + "default Loader is unsafe. Please read " + "https://msg.pyyaml.org/load for full details." + ) % method + + warnings.warn(message, YAMLLoadWarning, stacklevel=3) + +#------------------------------------------------------------------------------ +def scan(stream, Loader=Loader): + """ + Scan a YAML stream and produce scanning tokens. + """ + loader = Loader(stream) + try: + while loader.check_token(): + yield loader.get_token() + finally: + loader.dispose() + +def parse(stream, Loader=Loader): + """ + Parse a YAML stream and produce parsing events. + """ + loader = Loader(stream) + try: + while loader.check_event(): + yield loader.get_event() + finally: + loader.dispose() + +def compose(stream, Loader=Loader): + """ + Parse the first YAML document in a stream + and produce the corresponding representation tree. + """ + loader = Loader(stream) + try: + return loader.get_single_node() + finally: + loader.dispose() + +def compose_all(stream, Loader=Loader): + """ + Parse all YAML documents in a stream + and produce corresponding representation trees. + """ + loader = Loader(stream) + try: + while loader.check_node(): + yield loader.get_node() + finally: + loader.dispose() + +def load(stream, Loader=None): + """ + Parse the first YAML document in a stream + and produce the corresponding Python object. + """ + if Loader is None: + load_warning('load') + Loader = FullLoader + + loader = Loader(stream) + try: + return loader.get_single_data() + finally: + loader.dispose() + +def load_all(stream, Loader=None): + """ + Parse all YAML documents in a stream + and produce corresponding Python objects. + """ + if Loader is None: + load_warning('load_all') + Loader = FullLoader + + loader = Loader(stream) + try: + while loader.check_data(): + yield loader.get_data() + finally: + loader.dispose() + +def full_load(stream): + """ + Parse the first YAML document in a stream + and produce the corresponding Python object. + + Resolve all tags except those known to be + unsafe on untrusted input. + """ + return load(stream, FullLoader) + +def full_load_all(stream): + """ + Parse all YAML documents in a stream + and produce corresponding Python objects. + + Resolve all tags except those known to be + unsafe on untrusted input. + """ + return load_all(stream, FullLoader) + +def safe_load(stream): + """ + Parse the first YAML document in a stream + and produce the corresponding Python object. + + Resolve only basic YAML tags. This is known + to be safe for untrusted input. + """ + return load(stream, SafeLoader) + +def safe_load_all(stream): + """ + Parse all YAML documents in a stream + and produce corresponding Python objects. + + Resolve only basic YAML tags. This is known + to be safe for untrusted input. + """ + return load_all(stream, SafeLoader) + +def unsafe_load(stream): + """ + Parse the first YAML document in a stream + and produce the corresponding Python object. + + Resolve all tags, even those known to be + unsafe on untrusted input. + """ + return load(stream, UnsafeLoader) + +def unsafe_load_all(stream): + """ + Parse all YAML documents in a stream + and produce corresponding Python objects. + + Resolve all tags, even those known to be + unsafe on untrusted input. + """ + return load_all(stream, UnsafeLoader) + +def emit(events, stream=None, Dumper=Dumper, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None): + """ + Emit YAML parsing events into a stream. + If stream is None, return the produced string instead. + """ + getvalue = None + if stream is None: + stream = io.StringIO() + getvalue = stream.getvalue + dumper = Dumper(stream, canonical=canonical, indent=indent, width=width, + allow_unicode=allow_unicode, line_break=line_break) + try: + for event in events: + dumper.emit(event) + finally: + dumper.dispose() + if getvalue: + return getvalue() + +def serialize_all(nodes, stream=None, Dumper=Dumper, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None): + """ + Serialize a sequence of representation trees into a YAML stream. + If stream is None, return the produced string instead. + """ + getvalue = None + if stream is None: + if encoding is None: + stream = io.StringIO() + else: + stream = io.BytesIO() + getvalue = stream.getvalue + dumper = Dumper(stream, canonical=canonical, indent=indent, width=width, + allow_unicode=allow_unicode, line_break=line_break, + encoding=encoding, version=version, tags=tags, + explicit_start=explicit_start, explicit_end=explicit_end) + try: + dumper.open() + for node in nodes: + dumper.serialize(node) + dumper.close() + finally: + dumper.dispose() + if getvalue: + return getvalue() + +def serialize(node, stream=None, Dumper=Dumper, **kwds): + """ + Serialize a representation tree into a YAML stream. + If stream is None, return the produced string instead. + """ + return serialize_all([node], stream, Dumper=Dumper, **kwds) + +def dump_all(documents, stream=None, Dumper=Dumper, + default_style=None, default_flow_style=False, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None, sort_keys=True): + """ + Serialize a sequence of Python objects into a YAML stream. + If stream is None, return the produced string instead. + """ + getvalue = None + if stream is None: + if encoding is None: + stream = io.StringIO() + else: + stream = io.BytesIO() + getvalue = stream.getvalue + dumper = Dumper(stream, default_style=default_style, + default_flow_style=default_flow_style, + canonical=canonical, indent=indent, width=width, + allow_unicode=allow_unicode, line_break=line_break, + encoding=encoding, version=version, tags=tags, + explicit_start=explicit_start, explicit_end=explicit_end, sort_keys=sort_keys) + try: + dumper.open() + for data in documents: + dumper.represent(data) + dumper.close() + finally: + dumper.dispose() + if getvalue: + return getvalue() + +def dump(data, stream=None, Dumper=Dumper, **kwds): + """ + Serialize a Python object into a YAML stream. + If stream is None, return the produced string instead. + """ + return dump_all([data], stream, Dumper=Dumper, **kwds) + +def safe_dump_all(documents, stream=None, **kwds): + """ + Serialize a sequence of Python objects into a YAML stream. + Produce only basic YAML tags. + If stream is None, return the produced string instead. + """ + return dump_all(documents, stream, Dumper=SafeDumper, **kwds) + +def safe_dump(data, stream=None, **kwds): + """ + Serialize a Python object into a YAML stream. + Produce only basic YAML tags. + If stream is None, return the produced string instead. + """ + return dump_all([data], stream, Dumper=SafeDumper, **kwds) + +def add_implicit_resolver(tag, regexp, first=None, + Loader=None, Dumper=Dumper): + """ + Add an implicit scalar detector. + If an implicit scalar value matches the given regexp, + the corresponding tag is assigned to the scalar. + first is a sequence of possible initial characters or None. + """ + if Loader is None: + loader.Loader.add_implicit_resolver(tag, regexp, first) + loader.FullLoader.add_implicit_resolver(tag, regexp, first) + loader.UnsafeLoader.add_implicit_resolver(tag, regexp, first) + else: + Loader.add_implicit_resolver(tag, regexp, first) + Dumper.add_implicit_resolver(tag, regexp, first) + +def add_path_resolver(tag, path, kind=None, Loader=None, Dumper=Dumper): + """ + Add a path based resolver for the given tag. + A path is a list of keys that forms a path + to a node in the representation tree. + Keys can be string values, integers, or None. + """ + if Loader is None: + loader.Loader.add_path_resolver(tag, path, kind) + loader.FullLoader.add_path_resolver(tag, path, kind) + loader.UnsafeLoader.add_path_resolver(tag, path, kind) + else: + Loader.add_path_resolver(tag, path, kind) + Dumper.add_path_resolver(tag, path, kind) + +def add_constructor(tag, constructor, Loader=None): + """ + Add a constructor for the given tag. + Constructor is a function that accepts a Loader instance + and a node object and produces the corresponding Python object. + """ + if Loader is None: + loader.Loader.add_constructor(tag, constructor) + loader.FullLoader.add_constructor(tag, constructor) + loader.UnsafeLoader.add_constructor(tag, constructor) + else: + Loader.add_constructor(tag, constructor) + +def add_multi_constructor(tag_prefix, multi_constructor, Loader=None): + """ + Add a multi-constructor for the given tag prefix. + Multi-constructor is called for a node if its tag starts with tag_prefix. + Multi-constructor accepts a Loader instance, a tag suffix, + and a node object and produces the corresponding Python object. + """ + if Loader is None: + loader.Loader.add_multi_constructor(tag_prefix, multi_constructor) + loader.FullLoader.add_multi_constructor(tag_prefix, multi_constructor) + loader.UnsafeLoader.add_multi_constructor(tag_prefix, multi_constructor) + else: + Loader.add_multi_constructor(tag_prefix, multi_constructor) + +def add_representer(data_type, representer, Dumper=Dumper): + """ + Add a representer for the given type. + Representer is a function accepting a Dumper instance + and an instance of the given data type + and producing the corresponding representation node. + """ + Dumper.add_representer(data_type, representer) + +def add_multi_representer(data_type, multi_representer, Dumper=Dumper): + """ + Add a representer for the given type. + Multi-representer is a function accepting a Dumper instance + and an instance of the given data type or subtype + and producing the corresponding representation node. + """ + Dumper.add_multi_representer(data_type, multi_representer) + +class YAMLObjectMetaclass(type): + """ + The metaclass for YAMLObject. + """ + def __init__(cls, name, bases, kwds): + super(YAMLObjectMetaclass, cls).__init__(name, bases, kwds) + if 'yaml_tag' in kwds and kwds['yaml_tag'] is not None: + if isinstance(cls.yaml_loader, list): + for loader in cls.yaml_loader: + loader.add_constructor(cls.yaml_tag, cls.from_yaml) + else: + cls.yaml_loader.add_constructor(cls.yaml_tag, cls.from_yaml) + + cls.yaml_dumper.add_representer(cls, cls.to_yaml) + +class YAMLObject(metaclass=YAMLObjectMetaclass): + """ + An object that can dump itself to a YAML stream + and load itself from a YAML stream. + """ + + __slots__ = () # no direct instantiation, so allow immutable subclasses + + yaml_loader = [Loader, FullLoader, UnsafeLoader] + yaml_dumper = Dumper + + yaml_tag = None + yaml_flow_style = None + + @classmethod + def from_yaml(cls, loader, node): + """ + Convert a representation node to a Python object. + """ + return loader.construct_yaml_object(node, cls) + + @classmethod + def to_yaml(cls, dumper, data): + """ + Convert a Python object to a representation node. + """ + return dumper.represent_yaml_object(cls.yaml_tag, data, cls, + flow_style=cls.yaml_flow_style) + diff --git a/third_party/python/PyYAML/lib3/yaml/composer.py b/third_party/python/PyYAML/lib3/yaml/composer.py new file mode 100644 index 0000000000..6d15cb40e3 --- /dev/null +++ b/third_party/python/PyYAML/lib3/yaml/composer.py @@ -0,0 +1,139 @@ + +__all__ = ['Composer', 'ComposerError'] + +from .error import MarkedYAMLError +from .events import * +from .nodes import * + +class ComposerError(MarkedYAMLError): + pass + +class Composer: + + def __init__(self): + self.anchors = {} + + def check_node(self): + # Drop the STREAM-START event. + if self.check_event(StreamStartEvent): + self.get_event() + + # If there are more documents available? + return not self.check_event(StreamEndEvent) + + def get_node(self): + # Get the root node of the next document. + if not self.check_event(StreamEndEvent): + return self.compose_document() + + def get_single_node(self): + # Drop the STREAM-START event. + self.get_event() + + # Compose a document if the stream is not empty. + document = None + if not self.check_event(StreamEndEvent): + document = self.compose_document() + + # Ensure that the stream contains no more documents. + if not self.check_event(StreamEndEvent): + event = self.get_event() + raise ComposerError("expected a single document in the stream", + document.start_mark, "but found another document", + event.start_mark) + + # Drop the STREAM-END event. + self.get_event() + + return document + + def compose_document(self): + # Drop the DOCUMENT-START event. + self.get_event() + + # Compose the root node. + node = self.compose_node(None, None) + + # Drop the DOCUMENT-END event. + self.get_event() + + self.anchors = {} + return node + + def compose_node(self, parent, index): + if self.check_event(AliasEvent): + event = self.get_event() + anchor = event.anchor + if anchor not in self.anchors: + raise ComposerError(None, None, "found undefined alias %r" + % anchor, event.start_mark) + return self.anchors[anchor] + event = self.peek_event() + anchor = event.anchor + if anchor is not None: + if anchor in self.anchors: + raise ComposerError("found duplicate anchor %r; first occurrence" + % anchor, self.anchors[anchor].start_mark, + "second occurrence", event.start_mark) + self.descend_resolver(parent, index) + if self.check_event(ScalarEvent): + node = self.compose_scalar_node(anchor) + elif self.check_event(SequenceStartEvent): + node = self.compose_sequence_node(anchor) + elif self.check_event(MappingStartEvent): + node = self.compose_mapping_node(anchor) + self.ascend_resolver() + return node + + def compose_scalar_node(self, anchor): + event = self.get_event() + tag = event.tag + if tag is None or tag == '!': + tag = self.resolve(ScalarNode, event.value, event.implicit) + node = ScalarNode(tag, event.value, + event.start_mark, event.end_mark, style=event.style) + if anchor is not None: + self.anchors[anchor] = node + return node + + def compose_sequence_node(self, anchor): + start_event = self.get_event() + tag = start_event.tag + if tag is None or tag == '!': + tag = self.resolve(SequenceNode, None, start_event.implicit) + node = SequenceNode(tag, [], + start_event.start_mark, None, + flow_style=start_event.flow_style) + if anchor is not None: + self.anchors[anchor] = node + index = 0 + while not self.check_event(SequenceEndEvent): + node.value.append(self.compose_node(node, index)) + index += 1 + end_event = self.get_event() + node.end_mark = end_event.end_mark + return node + + def compose_mapping_node(self, anchor): + start_event = self.get_event() + tag = start_event.tag + if tag is None or tag == '!': + tag = self.resolve(MappingNode, None, start_event.implicit) + node = MappingNode(tag, [], + start_event.start_mark, None, + flow_style=start_event.flow_style) + if anchor is not None: + self.anchors[anchor] = node + while not self.check_event(MappingEndEvent): + #key_event = self.peek_event() + item_key = self.compose_node(node, None) + #if item_key in node.value: + # raise ComposerError("while composing a mapping", start_event.start_mark, + # "found duplicate key", key_event.start_mark) + item_value = self.compose_node(node, item_key) + #node.value[item_key] = item_value + node.value.append((item_key, item_value)) + end_event = self.get_event() + node.end_mark = end_event.end_mark + return node + diff --git a/third_party/python/PyYAML/lib3/yaml/constructor.py b/third_party/python/PyYAML/lib3/yaml/constructor.py new file mode 100644 index 0000000000..619acd3070 --- /dev/null +++ b/third_party/python/PyYAML/lib3/yaml/constructor.py @@ -0,0 +1,748 @@ + +__all__ = [ + 'BaseConstructor', + 'SafeConstructor', + 'FullConstructor', + 'UnsafeConstructor', + 'Constructor', + 'ConstructorError' +] + +from .error import * +from .nodes import * + +import collections.abc, datetime, base64, binascii, re, sys, types + +class ConstructorError(MarkedYAMLError): + pass + +class BaseConstructor: + + yaml_constructors = {} + yaml_multi_constructors = {} + + def __init__(self): + self.constructed_objects = {} + self.recursive_objects = {} + self.state_generators = [] + self.deep_construct = False + + def check_data(self): + # If there are more documents available? + return self.check_node() + + def check_state_key(self, key): + """Block special attributes/methods from being set in a newly created + object, to prevent user-controlled methods from being called during + deserialization""" + if self.get_state_keys_blacklist_regexp().match(key): + raise ConstructorError(None, None, + "blacklisted key '%s' in instance state found" % (key,), None) + + def get_data(self): + # Construct and return the next document. + if self.check_node(): + return self.construct_document(self.get_node()) + + def get_single_data(self): + # Ensure that the stream contains a single document and construct it. + node = self.get_single_node() + if node is not None: + return self.construct_document(node) + return None + + def construct_document(self, node): + data = self.construct_object(node) + while self.state_generators: + state_generators = self.state_generators + self.state_generators = [] + for generator in state_generators: + for dummy in generator: + pass + self.constructed_objects = {} + self.recursive_objects = {} + self.deep_construct = False + return data + + def construct_object(self, node, deep=False): + if node in self.constructed_objects: + return self.constructed_objects[node] + if deep: + old_deep = self.deep_construct + self.deep_construct = True + if node in self.recursive_objects: + raise ConstructorError(None, None, + "found unconstructable recursive node", node.start_mark) + self.recursive_objects[node] = None + constructor = None + tag_suffix = None + if node.tag in self.yaml_constructors: + constructor = self.yaml_constructors[node.tag] + else: + for tag_prefix in self.yaml_multi_constructors: + if tag_prefix is not None and node.tag.startswith(tag_prefix): + tag_suffix = node.tag[len(tag_prefix):] + constructor = self.yaml_multi_constructors[tag_prefix] + break + else: + if None in self.yaml_multi_constructors: + tag_suffix = node.tag + constructor = self.yaml_multi_constructors[None] + elif None in self.yaml_constructors: + constructor = self.yaml_constructors[None] + elif isinstance(node, ScalarNode): + constructor = self.__class__.construct_scalar + elif isinstance(node, SequenceNode): + constructor = self.__class__.construct_sequence + elif isinstance(node, MappingNode): + constructor = self.__class__.construct_mapping + if tag_suffix is None: + data = constructor(self, node) + else: + data = constructor(self, tag_suffix, node) + if isinstance(data, types.GeneratorType): + generator = data + data = next(generator) + if self.deep_construct: + for dummy in generator: + pass + else: + self.state_generators.append(generator) + self.constructed_objects[node] = data + del self.recursive_objects[node] + if deep: + self.deep_construct = old_deep + return data + + def construct_scalar(self, node): + if not isinstance(node, ScalarNode): + raise ConstructorError(None, None, + "expected a scalar node, but found %s" % node.id, + node.start_mark) + return node.value + + def construct_sequence(self, node, deep=False): + if not isinstance(node, SequenceNode): + raise ConstructorError(None, None, + "expected a sequence node, but found %s" % node.id, + node.start_mark) + return [self.construct_object(child, deep=deep) + for child in node.value] + + def construct_mapping(self, node, deep=False): + if not isinstance(node, MappingNode): + raise ConstructorError(None, None, + "expected a mapping node, but found %s" % node.id, + node.start_mark) + mapping = {} + for key_node, value_node in node.value: + key = self.construct_object(key_node, deep=deep) + if not isinstance(key, collections.abc.Hashable): + raise ConstructorError("while constructing a mapping", node.start_mark, + "found unhashable key", key_node.start_mark) + value = self.construct_object(value_node, deep=deep) + mapping[key] = value + return mapping + + def construct_pairs(self, node, deep=False): + if not isinstance(node, MappingNode): + raise ConstructorError(None, None, + "expected a mapping node, but found %s" % node.id, + node.start_mark) + pairs = [] + for key_node, value_node in node.value: + key = self.construct_object(key_node, deep=deep) + value = self.construct_object(value_node, deep=deep) + pairs.append((key, value)) + return pairs + + @classmethod + def add_constructor(cls, tag, constructor): + if not 'yaml_constructors' in cls.__dict__: + cls.yaml_constructors = cls.yaml_constructors.copy() + cls.yaml_constructors[tag] = constructor + + @classmethod + def add_multi_constructor(cls, tag_prefix, multi_constructor): + if not 'yaml_multi_constructors' in cls.__dict__: + cls.yaml_multi_constructors = cls.yaml_multi_constructors.copy() + cls.yaml_multi_constructors[tag_prefix] = multi_constructor + +class SafeConstructor(BaseConstructor): + + def construct_scalar(self, node): + if isinstance(node, MappingNode): + for key_node, value_node in node.value: + if key_node.tag == 'tag:yaml.org,2002:value': + return self.construct_scalar(value_node) + return super().construct_scalar(node) + + def flatten_mapping(self, node): + merge = [] + index = 0 + while index < len(node.value): + key_node, value_node = node.value[index] + if key_node.tag == 'tag:yaml.org,2002:merge': + del node.value[index] + if isinstance(value_node, MappingNode): + self.flatten_mapping(value_node) + merge.extend(value_node.value) + elif isinstance(value_node, SequenceNode): + submerge = [] + for subnode in value_node.value: + if not isinstance(subnode, MappingNode): + raise ConstructorError("while constructing a mapping", + node.start_mark, + "expected a mapping for merging, but found %s" + % subnode.id, subnode.start_mark) + self.flatten_mapping(subnode) + submerge.append(subnode.value) + submerge.reverse() + for value in submerge: + merge.extend(value) + else: + raise ConstructorError("while constructing a mapping", node.start_mark, + "expected a mapping or list of mappings for merging, but found %s" + % value_node.id, value_node.start_mark) + elif key_node.tag == 'tag:yaml.org,2002:value': + key_node.tag = 'tag:yaml.org,2002:str' + index += 1 + else: + index += 1 + if merge: + node.value = merge + node.value + + def construct_mapping(self, node, deep=False): + if isinstance(node, MappingNode): + self.flatten_mapping(node) + return super().construct_mapping(node, deep=deep) + + def construct_yaml_null(self, node): + self.construct_scalar(node) + return None + + bool_values = { + 'yes': True, + 'no': False, + 'true': True, + 'false': False, + 'on': True, + 'off': False, + } + + def construct_yaml_bool(self, node): + value = self.construct_scalar(node) + return self.bool_values[value.lower()] + + def construct_yaml_int(self, node): + value = self.construct_scalar(node) + value = value.replace('_', '') + sign = +1 + if value[0] == '-': + sign = -1 + if value[0] in '+-': + value = value[1:] + if value == '0': + return 0 + elif value.startswith('0b'): + return sign*int(value[2:], 2) + elif value.startswith('0x'): + return sign*int(value[2:], 16) + elif value[0] == '0': + return sign*int(value, 8) + elif ':' in value: + digits = [int(part) for part in value.split(':')] + digits.reverse() + base = 1 + value = 0 + for digit in digits: + value += digit*base + base *= 60 + return sign*value + else: + return sign*int(value) + + inf_value = 1e300 + while inf_value != inf_value*inf_value: + inf_value *= inf_value + nan_value = -inf_value/inf_value # Trying to make a quiet NaN (like C99). + + def construct_yaml_float(self, node): + value = self.construct_scalar(node) + value = value.replace('_', '').lower() + sign = +1 + if value[0] == '-': + sign = -1 + if value[0] in '+-': + value = value[1:] + if value == '.inf': + return sign*self.inf_value + elif value == '.nan': + return self.nan_value + elif ':' in value: + digits = [float(part) for part in value.split(':')] + digits.reverse() + base = 1 + value = 0.0 + for digit in digits: + value += digit*base + base *= 60 + return sign*value + else: + return sign*float(value) + + def construct_yaml_binary(self, node): + try: + value = self.construct_scalar(node).encode('ascii') + except UnicodeEncodeError as exc: + raise ConstructorError(None, None, + "failed to convert base64 data into ascii: %s" % exc, + node.start_mark) + try: + if hasattr(base64, 'decodebytes'): + return base64.decodebytes(value) + else: + return base64.decodestring(value) + except binascii.Error as exc: + raise ConstructorError(None, None, + "failed to decode base64 data: %s" % exc, node.start_mark) + + timestamp_regexp = re.compile( + r'''^(?P[0-9][0-9][0-9][0-9]) + -(?P[0-9][0-9]?) + -(?P[0-9][0-9]?) + (?:(?:[Tt]|[ \t]+) + (?P[0-9][0-9]?) + :(?P[0-9][0-9]) + :(?P[0-9][0-9]) + (?:\.(?P[0-9]*))? + (?:[ \t]*(?PZ|(?P[-+])(?P[0-9][0-9]?) + (?::(?P[0-9][0-9]))?))?)?$''', re.X) + + def construct_yaml_timestamp(self, node): + value = self.construct_scalar(node) + match = self.timestamp_regexp.match(node.value) + values = match.groupdict() + year = int(values['year']) + month = int(values['month']) + day = int(values['day']) + if not values['hour']: + return datetime.date(year, month, day) + hour = int(values['hour']) + minute = int(values['minute']) + second = int(values['second']) + fraction = 0 + tzinfo = None + if values['fraction']: + fraction = values['fraction'][:6] + while len(fraction) < 6: + fraction += '0' + fraction = int(fraction) + if values['tz_sign']: + tz_hour = int(values['tz_hour']) + tz_minute = int(values['tz_minute'] or 0) + delta = datetime.timedelta(hours=tz_hour, minutes=tz_minute) + if values['tz_sign'] == '-': + delta = -delta + tzinfo = datetime.timezone(delta) + elif values['tz']: + tzinfo = datetime.timezone.utc + return datetime.datetime(year, month, day, hour, minute, second, fraction, + tzinfo=tzinfo) + + def construct_yaml_omap(self, node): + # Note: we do not check for duplicate keys, because it's too + # CPU-expensive. + omap = [] + yield omap + if not isinstance(node, SequenceNode): + raise ConstructorError("while constructing an ordered map", node.start_mark, + "expected a sequence, but found %s" % node.id, node.start_mark) + for subnode in node.value: + if not isinstance(subnode, MappingNode): + raise ConstructorError("while constructing an ordered map", node.start_mark, + "expected a mapping of length 1, but found %s" % subnode.id, + subnode.start_mark) + if len(subnode.value) != 1: + raise ConstructorError("while constructing an ordered map", node.start_mark, + "expected a single mapping item, but found %d items" % len(subnode.value), + subnode.start_mark) + key_node, value_node = subnode.value[0] + key = self.construct_object(key_node) + value = self.construct_object(value_node) + omap.append((key, value)) + + def construct_yaml_pairs(self, node): + # Note: the same code as `construct_yaml_omap`. + pairs = [] + yield pairs + if not isinstance(node, SequenceNode): + raise ConstructorError("while constructing pairs", node.start_mark, + "expected a sequence, but found %s" % node.id, node.start_mark) + for subnode in node.value: + if not isinstance(subnode, MappingNode): + raise ConstructorError("while constructing pairs", node.start_mark, + "expected a mapping of length 1, but found %s" % subnode.id, + subnode.start_mark) + if len(subnode.value) != 1: + raise ConstructorError("while constructing pairs", node.start_mark, + "expected a single mapping item, but found %d items" % len(subnode.value), + subnode.start_mark) + key_node, value_node = subnode.value[0] + key = self.construct_object(key_node) + value = self.construct_object(value_node) + pairs.append((key, value)) + + def construct_yaml_set(self, node): + data = set() + yield data + value = self.construct_mapping(node) + data.update(value) + + def construct_yaml_str(self, node): + return self.construct_scalar(node) + + def construct_yaml_seq(self, node): + data = [] + yield data + data.extend(self.construct_sequence(node)) + + def construct_yaml_map(self, node): + data = {} + yield data + value = self.construct_mapping(node) + data.update(value) + + def construct_yaml_object(self, node, cls): + data = cls.__new__(cls) + yield data + if hasattr(data, '__setstate__'): + state = self.construct_mapping(node, deep=True) + data.__setstate__(state) + else: + state = self.construct_mapping(node) + data.__dict__.update(state) + + def construct_undefined(self, node): + raise ConstructorError(None, None, + "could not determine a constructor for the tag %r" % node.tag, + node.start_mark) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:null', + SafeConstructor.construct_yaml_null) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:bool', + SafeConstructor.construct_yaml_bool) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:int', + SafeConstructor.construct_yaml_int) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:float', + SafeConstructor.construct_yaml_float) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:binary', + SafeConstructor.construct_yaml_binary) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:timestamp', + SafeConstructor.construct_yaml_timestamp) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:omap', + SafeConstructor.construct_yaml_omap) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:pairs', + SafeConstructor.construct_yaml_pairs) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:set', + SafeConstructor.construct_yaml_set) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:str', + SafeConstructor.construct_yaml_str) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:seq', + SafeConstructor.construct_yaml_seq) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:map', + SafeConstructor.construct_yaml_map) + +SafeConstructor.add_constructor(None, + SafeConstructor.construct_undefined) + +class FullConstructor(SafeConstructor): + # 'extend' is blacklisted because it is used by + # construct_python_object_apply to add `listitems` to a newly generate + # python instance + def get_state_keys_blacklist(self): + return ['^extend$', '^__.*__$'] + + def get_state_keys_blacklist_regexp(self): + if not hasattr(self, 'state_keys_blacklist_regexp'): + self.state_keys_blacklist_regexp = re.compile('(' + '|'.join(self.get_state_keys_blacklist()) + ')') + return self.state_keys_blacklist_regexp + + def construct_python_str(self, node): + return self.construct_scalar(node) + + def construct_python_unicode(self, node): + return self.construct_scalar(node) + + def construct_python_bytes(self, node): + try: + value = self.construct_scalar(node).encode('ascii') + except UnicodeEncodeError as exc: + raise ConstructorError(None, None, + "failed to convert base64 data into ascii: %s" % exc, + node.start_mark) + try: + if hasattr(base64, 'decodebytes'): + return base64.decodebytes(value) + else: + return base64.decodestring(value) + except binascii.Error as exc: + raise ConstructorError(None, None, + "failed to decode base64 data: %s" % exc, node.start_mark) + + def construct_python_long(self, node): + return self.construct_yaml_int(node) + + def construct_python_complex(self, node): + return complex(self.construct_scalar(node)) + + def construct_python_tuple(self, node): + return tuple(self.construct_sequence(node)) + + def find_python_module(self, name, mark, unsafe=False): + if not name: + raise ConstructorError("while constructing a Python module", mark, + "expected non-empty name appended to the tag", mark) + if unsafe: + try: + __import__(name) + except ImportError as exc: + raise ConstructorError("while constructing a Python module", mark, + "cannot find module %r (%s)" % (name, exc), mark) + if name not in sys.modules: + raise ConstructorError("while constructing a Python module", mark, + "module %r is not imported" % name, mark) + return sys.modules[name] + + def find_python_name(self, name, mark, unsafe=False): + if not name: + raise ConstructorError("while constructing a Python object", mark, + "expected non-empty name appended to the tag", mark) + if '.' in name: + module_name, object_name = name.rsplit('.', 1) + else: + module_name = 'builtins' + object_name = name + if unsafe: + try: + __import__(module_name) + except ImportError as exc: + raise ConstructorError("while constructing a Python object", mark, + "cannot find module %r (%s)" % (module_name, exc), mark) + if module_name not in sys.modules: + raise ConstructorError("while constructing a Python object", mark, + "module %r is not imported" % module_name, mark) + module = sys.modules[module_name] + if not hasattr(module, object_name): + raise ConstructorError("while constructing a Python object", mark, + "cannot find %r in the module %r" + % (object_name, module.__name__), mark) + return getattr(module, object_name) + + def construct_python_name(self, suffix, node): + value = self.construct_scalar(node) + if value: + raise ConstructorError("while constructing a Python name", node.start_mark, + "expected the empty value, but found %r" % value, node.start_mark) + return self.find_python_name(suffix, node.start_mark) + + def construct_python_module(self, suffix, node): + value = self.construct_scalar(node) + if value: + raise ConstructorError("while constructing a Python module", node.start_mark, + "expected the empty value, but found %r" % value, node.start_mark) + return self.find_python_module(suffix, node.start_mark) + + def make_python_instance(self, suffix, node, + args=None, kwds=None, newobj=False, unsafe=False): + if not args: + args = [] + if not kwds: + kwds = {} + cls = self.find_python_name(suffix, node.start_mark) + if not (unsafe or isinstance(cls, type)): + raise ConstructorError("while constructing a Python instance", node.start_mark, + "expected a class, but found %r" % type(cls), + node.start_mark) + if newobj and isinstance(cls, type): + return cls.__new__(cls, *args, **kwds) + else: + return cls(*args, **kwds) + + def set_python_instance_state(self, instance, state, unsafe=False): + if hasattr(instance, '__setstate__'): + instance.__setstate__(state) + else: + slotstate = {} + if isinstance(state, tuple) and len(state) == 2: + state, slotstate = state + if hasattr(instance, '__dict__'): + if not unsafe and state: + for key in state.keys(): + self.check_state_key(key) + instance.__dict__.update(state) + elif state: + slotstate.update(state) + for key, value in slotstate.items(): + if not unsafe: + self.check_state_key(key) + setattr(instance, key, value) + + def construct_python_object(self, suffix, node): + # Format: + # !!python/object:module.name { ... state ... } + instance = self.make_python_instance(suffix, node, newobj=True) + yield instance + deep = hasattr(instance, '__setstate__') + state = self.construct_mapping(node, deep=deep) + self.set_python_instance_state(instance, state) + + def construct_python_object_apply(self, suffix, node, newobj=False): + # Format: + # !!python/object/apply # (or !!python/object/new) + # args: [ ... arguments ... ] + # kwds: { ... keywords ... } + # state: ... state ... + # listitems: [ ... listitems ... ] + # dictitems: { ... dictitems ... } + # or short format: + # !!python/object/apply [ ... arguments ... ] + # The difference between !!python/object/apply and !!python/object/new + # is how an object is created, check make_python_instance for details. + if isinstance(node, SequenceNode): + args = self.construct_sequence(node, deep=True) + kwds = {} + state = {} + listitems = [] + dictitems = {} + else: + value = self.construct_mapping(node, deep=True) + args = value.get('args', []) + kwds = value.get('kwds', {}) + state = value.get('state', {}) + listitems = value.get('listitems', []) + dictitems = value.get('dictitems', {}) + instance = self.make_python_instance(suffix, node, args, kwds, newobj) + if state: + self.set_python_instance_state(instance, state) + if listitems: + instance.extend(listitems) + if dictitems: + for key in dictitems: + instance[key] = dictitems[key] + return instance + + def construct_python_object_new(self, suffix, node): + return self.construct_python_object_apply(suffix, node, newobj=True) + +FullConstructor.add_constructor( + 'tag:yaml.org,2002:python/none', + FullConstructor.construct_yaml_null) + +FullConstructor.add_constructor( + 'tag:yaml.org,2002:python/bool', + FullConstructor.construct_yaml_bool) + +FullConstructor.add_constructor( + 'tag:yaml.org,2002:python/str', + FullConstructor.construct_python_str) + +FullConstructor.add_constructor( + 'tag:yaml.org,2002:python/unicode', + FullConstructor.construct_python_unicode) + +FullConstructor.add_constructor( + 'tag:yaml.org,2002:python/bytes', + FullConstructor.construct_python_bytes) + +FullConstructor.add_constructor( + 'tag:yaml.org,2002:python/int', + FullConstructor.construct_yaml_int) + +FullConstructor.add_constructor( + 'tag:yaml.org,2002:python/long', + FullConstructor.construct_python_long) + +FullConstructor.add_constructor( + 'tag:yaml.org,2002:python/float', + FullConstructor.construct_yaml_float) + +FullConstructor.add_constructor( + 'tag:yaml.org,2002:python/complex', + FullConstructor.construct_python_complex) + +FullConstructor.add_constructor( + 'tag:yaml.org,2002:python/list', + FullConstructor.construct_yaml_seq) + +FullConstructor.add_constructor( + 'tag:yaml.org,2002:python/tuple', + FullConstructor.construct_python_tuple) + +FullConstructor.add_constructor( + 'tag:yaml.org,2002:python/dict', + FullConstructor.construct_yaml_map) + +FullConstructor.add_multi_constructor( + 'tag:yaml.org,2002:python/name:', + FullConstructor.construct_python_name) + +class UnsafeConstructor(FullConstructor): + + def find_python_module(self, name, mark): + return super(UnsafeConstructor, self).find_python_module(name, mark, unsafe=True) + + def find_python_name(self, name, mark): + return super(UnsafeConstructor, self).find_python_name(name, mark, unsafe=True) + + def make_python_instance(self, suffix, node, args=None, kwds=None, newobj=False): + return super(UnsafeConstructor, self).make_python_instance( + suffix, node, args, kwds, newobj, unsafe=True) + + def set_python_instance_state(self, instance, state): + return super(UnsafeConstructor, self).set_python_instance_state( + instance, state, unsafe=True) + +UnsafeConstructor.add_multi_constructor( + 'tag:yaml.org,2002:python/module:', + UnsafeConstructor.construct_python_module) + +UnsafeConstructor.add_multi_constructor( + 'tag:yaml.org,2002:python/object:', + UnsafeConstructor.construct_python_object) + +UnsafeConstructor.add_multi_constructor( + 'tag:yaml.org,2002:python/object/new:', + UnsafeConstructor.construct_python_object_new) + +UnsafeConstructor.add_multi_constructor( + 'tag:yaml.org,2002:python/object/apply:', + UnsafeConstructor.construct_python_object_apply) + +# Constructor is same as UnsafeConstructor. Need to leave this in place in case +# people have extended it directly. +class Constructor(UnsafeConstructor): + pass diff --git a/third_party/python/PyYAML/lib3/yaml/cyaml.py b/third_party/python/PyYAML/lib3/yaml/cyaml.py new file mode 100644 index 0000000000..0c21345879 --- /dev/null +++ b/third_party/python/PyYAML/lib3/yaml/cyaml.py @@ -0,0 +1,101 @@ + +__all__ = [ + 'CBaseLoader', 'CSafeLoader', 'CFullLoader', 'CUnsafeLoader', 'CLoader', + 'CBaseDumper', 'CSafeDumper', 'CDumper' +] + +from yaml._yaml import CParser, CEmitter + +from .constructor import * + +from .serializer import * +from .representer import * + +from .resolver import * + +class CBaseLoader(CParser, BaseConstructor, BaseResolver): + + def __init__(self, stream): + CParser.__init__(self, stream) + BaseConstructor.__init__(self) + BaseResolver.__init__(self) + +class CSafeLoader(CParser, SafeConstructor, Resolver): + + def __init__(self, stream): + CParser.__init__(self, stream) + SafeConstructor.__init__(self) + Resolver.__init__(self) + +class CFullLoader(CParser, FullConstructor, Resolver): + + def __init__(self, stream): + CParser.__init__(self, stream) + FullConstructor.__init__(self) + Resolver.__init__(self) + +class CUnsafeLoader(CParser, UnsafeConstructor, Resolver): + + def __init__(self, stream): + CParser.__init__(self, stream) + UnsafeConstructor.__init__(self) + Resolver.__init__(self) + +class CLoader(CParser, Constructor, Resolver): + + def __init__(self, stream): + CParser.__init__(self, stream) + Constructor.__init__(self) + Resolver.__init__(self) + +class CBaseDumper(CEmitter, BaseRepresenter, BaseResolver): + + def __init__(self, stream, + default_style=None, default_flow_style=False, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None, sort_keys=True): + CEmitter.__init__(self, stream, canonical=canonical, + indent=indent, width=width, encoding=encoding, + allow_unicode=allow_unicode, line_break=line_break, + explicit_start=explicit_start, explicit_end=explicit_end, + version=version, tags=tags) + Representer.__init__(self, default_style=default_style, + default_flow_style=default_flow_style, sort_keys=sort_keys) + Resolver.__init__(self) + +class CSafeDumper(CEmitter, SafeRepresenter, Resolver): + + def __init__(self, stream, + default_style=None, default_flow_style=False, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None, sort_keys=True): + CEmitter.__init__(self, stream, canonical=canonical, + indent=indent, width=width, encoding=encoding, + allow_unicode=allow_unicode, line_break=line_break, + explicit_start=explicit_start, explicit_end=explicit_end, + version=version, tags=tags) + SafeRepresenter.__init__(self, default_style=default_style, + default_flow_style=default_flow_style, sort_keys=sort_keys) + Resolver.__init__(self) + +class CDumper(CEmitter, Serializer, Representer, Resolver): + + def __init__(self, stream, + default_style=None, default_flow_style=False, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None, sort_keys=True): + CEmitter.__init__(self, stream, canonical=canonical, + indent=indent, width=width, encoding=encoding, + allow_unicode=allow_unicode, line_break=line_break, + explicit_start=explicit_start, explicit_end=explicit_end, + version=version, tags=tags) + Representer.__init__(self, default_style=default_style, + default_flow_style=default_flow_style, sort_keys=sort_keys) + Resolver.__init__(self) + diff --git a/third_party/python/PyYAML/lib3/yaml/dumper.py b/third_party/python/PyYAML/lib3/yaml/dumper.py new file mode 100644 index 0000000000..6aadba551f --- /dev/null +++ b/third_party/python/PyYAML/lib3/yaml/dumper.py @@ -0,0 +1,62 @@ + +__all__ = ['BaseDumper', 'SafeDumper', 'Dumper'] + +from .emitter import * +from .serializer import * +from .representer import * +from .resolver import * + +class BaseDumper(Emitter, Serializer, BaseRepresenter, BaseResolver): + + def __init__(self, stream, + default_style=None, default_flow_style=False, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None, sort_keys=True): + Emitter.__init__(self, stream, canonical=canonical, + indent=indent, width=width, + allow_unicode=allow_unicode, line_break=line_break) + Serializer.__init__(self, encoding=encoding, + explicit_start=explicit_start, explicit_end=explicit_end, + version=version, tags=tags) + Representer.__init__(self, default_style=default_style, + default_flow_style=default_flow_style, sort_keys=sort_keys) + Resolver.__init__(self) + +class SafeDumper(Emitter, Serializer, SafeRepresenter, Resolver): + + def __init__(self, stream, + default_style=None, default_flow_style=False, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None, sort_keys=True): + Emitter.__init__(self, stream, canonical=canonical, + indent=indent, width=width, + allow_unicode=allow_unicode, line_break=line_break) + Serializer.__init__(self, encoding=encoding, + explicit_start=explicit_start, explicit_end=explicit_end, + version=version, tags=tags) + SafeRepresenter.__init__(self, default_style=default_style, + default_flow_style=default_flow_style, sort_keys=sort_keys) + Resolver.__init__(self) + +class Dumper(Emitter, Serializer, Representer, Resolver): + + def __init__(self, stream, + default_style=None, default_flow_style=False, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None, sort_keys=True): + Emitter.__init__(self, stream, canonical=canonical, + indent=indent, width=width, + allow_unicode=allow_unicode, line_break=line_break) + Serializer.__init__(self, encoding=encoding, + explicit_start=explicit_start, explicit_end=explicit_end, + version=version, tags=tags) + Representer.__init__(self, default_style=default_style, + default_flow_style=default_flow_style, sort_keys=sort_keys) + Resolver.__init__(self) + diff --git a/third_party/python/PyYAML/lib3/yaml/emitter.py b/third_party/python/PyYAML/lib3/yaml/emitter.py new file mode 100644 index 0000000000..a664d01116 --- /dev/null +++ b/third_party/python/PyYAML/lib3/yaml/emitter.py @@ -0,0 +1,1137 @@ + +# Emitter expects events obeying the following grammar: +# stream ::= STREAM-START document* STREAM-END +# document ::= DOCUMENT-START node DOCUMENT-END +# node ::= SCALAR | sequence | mapping +# sequence ::= SEQUENCE-START node* SEQUENCE-END +# mapping ::= MAPPING-START (node node)* MAPPING-END + +__all__ = ['Emitter', 'EmitterError'] + +from .error import YAMLError +from .events import * + +class EmitterError(YAMLError): + pass + +class ScalarAnalysis: + def __init__(self, scalar, empty, multiline, + allow_flow_plain, allow_block_plain, + allow_single_quoted, allow_double_quoted, + allow_block): + self.scalar = scalar + self.empty = empty + self.multiline = multiline + self.allow_flow_plain = allow_flow_plain + self.allow_block_plain = allow_block_plain + self.allow_single_quoted = allow_single_quoted + self.allow_double_quoted = allow_double_quoted + self.allow_block = allow_block + +class Emitter: + + DEFAULT_TAG_PREFIXES = { + '!' : '!', + 'tag:yaml.org,2002:' : '!!', + } + + def __init__(self, stream, canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None): + + # The stream should have the methods `write` and possibly `flush`. + self.stream = stream + + # Encoding can be overridden by STREAM-START. + self.encoding = None + + # Emitter is a state machine with a stack of states to handle nested + # structures. + self.states = [] + self.state = self.expect_stream_start + + # Current event and the event queue. + self.events = [] + self.event = None + + # The current indentation level and the stack of previous indents. + self.indents = [] + self.indent = None + + # Flow level. + self.flow_level = 0 + + # Contexts. + self.root_context = False + self.sequence_context = False + self.mapping_context = False + self.simple_key_context = False + + # Characteristics of the last emitted character: + # - current position. + # - is it a whitespace? + # - is it an indention character + # (indentation space, '-', '?', or ':')? + self.line = 0 + self.column = 0 + self.whitespace = True + self.indention = True + + # Whether the document requires an explicit document indicator + self.open_ended = False + + # Formatting details. + self.canonical = canonical + self.allow_unicode = allow_unicode + self.best_indent = 2 + if indent and 1 < indent < 10: + self.best_indent = indent + self.best_width = 80 + if width and width > self.best_indent*2: + self.best_width = width + self.best_line_break = '\n' + if line_break in ['\r', '\n', '\r\n']: + self.best_line_break = line_break + + # Tag prefixes. + self.tag_prefixes = None + + # Prepared anchor and tag. + self.prepared_anchor = None + self.prepared_tag = None + + # Scalar analysis and style. + self.analysis = None + self.style = None + + def dispose(self): + # Reset the state attributes (to clear self-references) + self.states = [] + self.state = None + + def emit(self, event): + self.events.append(event) + while not self.need_more_events(): + self.event = self.events.pop(0) + self.state() + self.event = None + + # In some cases, we wait for a few next events before emitting. + + def need_more_events(self): + if not self.events: + return True + event = self.events[0] + if isinstance(event, DocumentStartEvent): + return self.need_events(1) + elif isinstance(event, SequenceStartEvent): + return self.need_events(2) + elif isinstance(event, MappingStartEvent): + return self.need_events(3) + else: + return False + + def need_events(self, count): + level = 0 + for event in self.events[1:]: + if isinstance(event, (DocumentStartEvent, CollectionStartEvent)): + level += 1 + elif isinstance(event, (DocumentEndEvent, CollectionEndEvent)): + level -= 1 + elif isinstance(event, StreamEndEvent): + level = -1 + if level < 0: + return False + return (len(self.events) < count+1) + + def increase_indent(self, flow=False, indentless=False): + self.indents.append(self.indent) + if self.indent is None: + if flow: + self.indent = self.best_indent + else: + self.indent = 0 + elif not indentless: + self.indent += self.best_indent + + # States. + + # Stream handlers. + + def expect_stream_start(self): + if isinstance(self.event, StreamStartEvent): + if self.event.encoding and not hasattr(self.stream, 'encoding'): + self.encoding = self.event.encoding + self.write_stream_start() + self.state = self.expect_first_document_start + else: + raise EmitterError("expected StreamStartEvent, but got %s" + % self.event) + + def expect_nothing(self): + raise EmitterError("expected nothing, but got %s" % self.event) + + # Document handlers. + + def expect_first_document_start(self): + return self.expect_document_start(first=True) + + def expect_document_start(self, first=False): + if isinstance(self.event, DocumentStartEvent): + if (self.event.version or self.event.tags) and self.open_ended: + self.write_indicator('...', True) + self.write_indent() + if self.event.version: + version_text = self.prepare_version(self.event.version) + self.write_version_directive(version_text) + self.tag_prefixes = self.DEFAULT_TAG_PREFIXES.copy() + if self.event.tags: + handles = sorted(self.event.tags.keys()) + for handle in handles: + prefix = self.event.tags[handle] + self.tag_prefixes[prefix] = handle + handle_text = self.prepare_tag_handle(handle) + prefix_text = self.prepare_tag_prefix(prefix) + self.write_tag_directive(handle_text, prefix_text) + implicit = (first and not self.event.explicit and not self.canonical + and not self.event.version and not self.event.tags + and not self.check_empty_document()) + if not implicit: + self.write_indent() + self.write_indicator('---', True) + if self.canonical: + self.write_indent() + self.state = self.expect_document_root + elif isinstance(self.event, StreamEndEvent): + if self.open_ended: + self.write_indicator('...', True) + self.write_indent() + self.write_stream_end() + self.state = self.expect_nothing + else: + raise EmitterError("expected DocumentStartEvent, but got %s" + % self.event) + + def expect_document_end(self): + if isinstance(self.event, DocumentEndEvent): + self.write_indent() + if self.event.explicit: + self.write_indicator('...', True) + self.write_indent() + self.flush_stream() + self.state = self.expect_document_start + else: + raise EmitterError("expected DocumentEndEvent, but got %s" + % self.event) + + def expect_document_root(self): + self.states.append(self.expect_document_end) + self.expect_node(root=True) + + # Node handlers. + + def expect_node(self, root=False, sequence=False, mapping=False, + simple_key=False): + self.root_context = root + self.sequence_context = sequence + self.mapping_context = mapping + self.simple_key_context = simple_key + if isinstance(self.event, AliasEvent): + self.expect_alias() + elif isinstance(self.event, (ScalarEvent, CollectionStartEvent)): + self.process_anchor('&') + self.process_tag() + if isinstance(self.event, ScalarEvent): + self.expect_scalar() + elif isinstance(self.event, SequenceStartEvent): + if self.flow_level or self.canonical or self.event.flow_style \ + or self.check_empty_sequence(): + self.expect_flow_sequence() + else: + self.expect_block_sequence() + elif isinstance(self.event, MappingStartEvent): + if self.flow_level or self.canonical or self.event.flow_style \ + or self.check_empty_mapping(): + self.expect_flow_mapping() + else: + self.expect_block_mapping() + else: + raise EmitterError("expected NodeEvent, but got %s" % self.event) + + def expect_alias(self): + if self.event.anchor is None: + raise EmitterError("anchor is not specified for alias") + self.process_anchor('*') + self.state = self.states.pop() + + def expect_scalar(self): + self.increase_indent(flow=True) + self.process_scalar() + self.indent = self.indents.pop() + self.state = self.states.pop() + + # Flow sequence handlers. + + def expect_flow_sequence(self): + self.write_indicator('[', True, whitespace=True) + self.flow_level += 1 + self.increase_indent(flow=True) + self.state = self.expect_first_flow_sequence_item + + def expect_first_flow_sequence_item(self): + if isinstance(self.event, SequenceEndEvent): + self.indent = self.indents.pop() + self.flow_level -= 1 + self.write_indicator(']', False) + self.state = self.states.pop() + else: + if self.canonical or self.column > self.best_width: + self.write_indent() + self.states.append(self.expect_flow_sequence_item) + self.expect_node(sequence=True) + + def expect_flow_sequence_item(self): + if isinstance(self.event, SequenceEndEvent): + self.indent = self.indents.pop() + self.flow_level -= 1 + if self.canonical: + self.write_indicator(',', False) + self.write_indent() + self.write_indicator(']', False) + self.state = self.states.pop() + else: + self.write_indicator(',', False) + if self.canonical or self.column > self.best_width: + self.write_indent() + self.states.append(self.expect_flow_sequence_item) + self.expect_node(sequence=True) + + # Flow mapping handlers. + + def expect_flow_mapping(self): + self.write_indicator('{', True, whitespace=True) + self.flow_level += 1 + self.increase_indent(flow=True) + self.state = self.expect_first_flow_mapping_key + + def expect_first_flow_mapping_key(self): + if isinstance(self.event, MappingEndEvent): + self.indent = self.indents.pop() + self.flow_level -= 1 + self.write_indicator('}', False) + self.state = self.states.pop() + else: + if self.canonical or self.column > self.best_width: + self.write_indent() + if not self.canonical and self.check_simple_key(): + self.states.append(self.expect_flow_mapping_simple_value) + self.expect_node(mapping=True, simple_key=True) + else: + self.write_indicator('?', True) + self.states.append(self.expect_flow_mapping_value) + self.expect_node(mapping=True) + + def expect_flow_mapping_key(self): + if isinstance(self.event, MappingEndEvent): + self.indent = self.indents.pop() + self.flow_level -= 1 + if self.canonical: + self.write_indicator(',', False) + self.write_indent() + self.write_indicator('}', False) + self.state = self.states.pop() + else: + self.write_indicator(',', False) + if self.canonical or self.column > self.best_width: + self.write_indent() + if not self.canonical and self.check_simple_key(): + self.states.append(self.expect_flow_mapping_simple_value) + self.expect_node(mapping=True, simple_key=True) + else: + self.write_indicator('?', True) + self.states.append(self.expect_flow_mapping_value) + self.expect_node(mapping=True) + + def expect_flow_mapping_simple_value(self): + self.write_indicator(':', False) + self.states.append(self.expect_flow_mapping_key) + self.expect_node(mapping=True) + + def expect_flow_mapping_value(self): + if self.canonical or self.column > self.best_width: + self.write_indent() + self.write_indicator(':', True) + self.states.append(self.expect_flow_mapping_key) + self.expect_node(mapping=True) + + # Block sequence handlers. + + def expect_block_sequence(self): + indentless = (self.mapping_context and not self.indention) + self.increase_indent(flow=False, indentless=indentless) + self.state = self.expect_first_block_sequence_item + + def expect_first_block_sequence_item(self): + return self.expect_block_sequence_item(first=True) + + def expect_block_sequence_item(self, first=False): + if not first and isinstance(self.event, SequenceEndEvent): + self.indent = self.indents.pop() + self.state = self.states.pop() + else: + self.write_indent() + self.write_indicator('-', True, indention=True) + self.states.append(self.expect_block_sequence_item) + self.expect_node(sequence=True) + + # Block mapping handlers. + + def expect_block_mapping(self): + self.increase_indent(flow=False) + self.state = self.expect_first_block_mapping_key + + def expect_first_block_mapping_key(self): + return self.expect_block_mapping_key(first=True) + + def expect_block_mapping_key(self, first=False): + if not first and isinstance(self.event, MappingEndEvent): + self.indent = self.indents.pop() + self.state = self.states.pop() + else: + self.write_indent() + if self.check_simple_key(): + self.states.append(self.expect_block_mapping_simple_value) + self.expect_node(mapping=True, simple_key=True) + else: + self.write_indicator('?', True, indention=True) + self.states.append(self.expect_block_mapping_value) + self.expect_node(mapping=True) + + def expect_block_mapping_simple_value(self): + self.write_indicator(':', False) + self.states.append(self.expect_block_mapping_key) + self.expect_node(mapping=True) + + def expect_block_mapping_value(self): + self.write_indent() + self.write_indicator(':', True, indention=True) + self.states.append(self.expect_block_mapping_key) + self.expect_node(mapping=True) + + # Checkers. + + def check_empty_sequence(self): + return (isinstance(self.event, SequenceStartEvent) and self.events + and isinstance(self.events[0], SequenceEndEvent)) + + def check_empty_mapping(self): + return (isinstance(self.event, MappingStartEvent) and self.events + and isinstance(self.events[0], MappingEndEvent)) + + def check_empty_document(self): + if not isinstance(self.event, DocumentStartEvent) or not self.events: + return False + event = self.events[0] + return (isinstance(event, ScalarEvent) and event.anchor is None + and event.tag is None and event.implicit and event.value == '') + + def check_simple_key(self): + length = 0 + if isinstance(self.event, NodeEvent) and self.event.anchor is not None: + if self.prepared_anchor is None: + self.prepared_anchor = self.prepare_anchor(self.event.anchor) + length += len(self.prepared_anchor) + if isinstance(self.event, (ScalarEvent, CollectionStartEvent)) \ + and self.event.tag is not None: + if self.prepared_tag is None: + self.prepared_tag = self.prepare_tag(self.event.tag) + length += len(self.prepared_tag) + if isinstance(self.event, ScalarEvent): + if self.analysis is None: + self.analysis = self.analyze_scalar(self.event.value) + length += len(self.analysis.scalar) + return (length < 128 and (isinstance(self.event, AliasEvent) + or (isinstance(self.event, ScalarEvent) + and not self.analysis.empty and not self.analysis.multiline) + or self.check_empty_sequence() or self.check_empty_mapping())) + + # Anchor, Tag, and Scalar processors. + + def process_anchor(self, indicator): + if self.event.anchor is None: + self.prepared_anchor = None + return + if self.prepared_anchor is None: + self.prepared_anchor = self.prepare_anchor(self.event.anchor) + if self.prepared_anchor: + self.write_indicator(indicator+self.prepared_anchor, True) + self.prepared_anchor = None + + def process_tag(self): + tag = self.event.tag + if isinstance(self.event, ScalarEvent): + if self.style is None: + self.style = self.choose_scalar_style() + if ((not self.canonical or tag is None) and + ((self.style == '' and self.event.implicit[0]) + or (self.style != '' and self.event.implicit[1]))): + self.prepared_tag = None + return + if self.event.implicit[0] and tag is None: + tag = '!' + self.prepared_tag = None + else: + if (not self.canonical or tag is None) and self.event.implicit: + self.prepared_tag = None + return + if tag is None: + raise EmitterError("tag is not specified") + if self.prepared_tag is None: + self.prepared_tag = self.prepare_tag(tag) + if self.prepared_tag: + self.write_indicator(self.prepared_tag, True) + self.prepared_tag = None + + def choose_scalar_style(self): + if self.analysis is None: + self.analysis = self.analyze_scalar(self.event.value) + if self.event.style == '"' or self.canonical: + return '"' + if not self.event.style and self.event.implicit[0]: + if (not (self.simple_key_context and + (self.analysis.empty or self.analysis.multiline)) + and (self.flow_level and self.analysis.allow_flow_plain + or (not self.flow_level and self.analysis.allow_block_plain))): + return '' + if self.event.style and self.event.style in '|>': + if (not self.flow_level and not self.simple_key_context + and self.analysis.allow_block): + return self.event.style + if not self.event.style or self.event.style == '\'': + if (self.analysis.allow_single_quoted and + not (self.simple_key_context and self.analysis.multiline)): + return '\'' + return '"' + + def process_scalar(self): + if self.analysis is None: + self.analysis = self.analyze_scalar(self.event.value) + if self.style is None: + self.style = self.choose_scalar_style() + split = (not self.simple_key_context) + #if self.analysis.multiline and split \ + # and (not self.style or self.style in '\'\"'): + # self.write_indent() + if self.style == '"': + self.write_double_quoted(self.analysis.scalar, split) + elif self.style == '\'': + self.write_single_quoted(self.analysis.scalar, split) + elif self.style == '>': + self.write_folded(self.analysis.scalar) + elif self.style == '|': + self.write_literal(self.analysis.scalar) + else: + self.write_plain(self.analysis.scalar, split) + self.analysis = None + self.style = None + + # Analyzers. + + def prepare_version(self, version): + major, minor = version + if major != 1: + raise EmitterError("unsupported YAML version: %d.%d" % (major, minor)) + return '%d.%d' % (major, minor) + + def prepare_tag_handle(self, handle): + if not handle: + raise EmitterError("tag handle must not be empty") + if handle[0] != '!' or handle[-1] != '!': + raise EmitterError("tag handle must start and end with '!': %r" % handle) + for ch in handle[1:-1]: + if not ('0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ + or ch in '-_'): + raise EmitterError("invalid character %r in the tag handle: %r" + % (ch, handle)) + return handle + + def prepare_tag_prefix(self, prefix): + if not prefix: + raise EmitterError("tag prefix must not be empty") + chunks = [] + start = end = 0 + if prefix[0] == '!': + end = 1 + while end < len(prefix): + ch = prefix[end] + if '0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ + or ch in '-;/?!:@&=+$,_.~*\'()[]': + end += 1 + else: + if start < end: + chunks.append(prefix[start:end]) + start = end = end+1 + data = ch.encode('utf-8') + for ch in data: + chunks.append('%%%02X' % ord(ch)) + if start < end: + chunks.append(prefix[start:end]) + return ''.join(chunks) + + def prepare_tag(self, tag): + if not tag: + raise EmitterError("tag must not be empty") + if tag == '!': + return tag + handle = None + suffix = tag + prefixes = sorted(self.tag_prefixes.keys()) + for prefix in prefixes: + if tag.startswith(prefix) \ + and (prefix == '!' or len(prefix) < len(tag)): + handle = self.tag_prefixes[prefix] + suffix = tag[len(prefix):] + chunks = [] + start = end = 0 + while end < len(suffix): + ch = suffix[end] + if '0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ + or ch in '-;/?:@&=+$,_.~*\'()[]' \ + or (ch == '!' and handle != '!'): + end += 1 + else: + if start < end: + chunks.append(suffix[start:end]) + start = end = end+1 + data = ch.encode('utf-8') + for ch in data: + chunks.append('%%%02X' % ch) + if start < end: + chunks.append(suffix[start:end]) + suffix_text = ''.join(chunks) + if handle: + return '%s%s' % (handle, suffix_text) + else: + return '!<%s>' % suffix_text + + def prepare_anchor(self, anchor): + if not anchor: + raise EmitterError("anchor must not be empty") + for ch in anchor: + if not ('0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ + or ch in '-_'): + raise EmitterError("invalid character %r in the anchor: %r" + % (ch, anchor)) + return anchor + + def analyze_scalar(self, scalar): + + # Empty scalar is a special case. + if not scalar: + return ScalarAnalysis(scalar=scalar, empty=True, multiline=False, + allow_flow_plain=False, allow_block_plain=True, + allow_single_quoted=True, allow_double_quoted=True, + allow_block=False) + + # Indicators and special characters. + block_indicators = False + flow_indicators = False + line_breaks = False + special_characters = False + + # Important whitespace combinations. + leading_space = False + leading_break = False + trailing_space = False + trailing_break = False + break_space = False + space_break = False + + # Check document indicators. + if scalar.startswith('---') or scalar.startswith('...'): + block_indicators = True + flow_indicators = True + + # First character or preceded by a whitespace. + preceded_by_whitespace = True + + # Last character or followed by a whitespace. + followed_by_whitespace = (len(scalar) == 1 or + scalar[1] in '\0 \t\r\n\x85\u2028\u2029') + + # The previous character is a space. + previous_space = False + + # The previous character is a break. + previous_break = False + + index = 0 + while index < len(scalar): + ch = scalar[index] + + # Check for indicators. + if index == 0: + # Leading indicators are special characters. + if ch in '#,[]{}&*!|>\'\"%@`': + flow_indicators = True + block_indicators = True + if ch in '?:': + flow_indicators = True + if followed_by_whitespace: + block_indicators = True + if ch == '-' and followed_by_whitespace: + flow_indicators = True + block_indicators = True + else: + # Some indicators cannot appear within a scalar as well. + if ch in ',?[]{}': + flow_indicators = True + if ch == ':': + flow_indicators = True + if followed_by_whitespace: + block_indicators = True + if ch == '#' and preceded_by_whitespace: + flow_indicators = True + block_indicators = True + + # Check for line breaks, special, and unicode characters. + if ch in '\n\x85\u2028\u2029': + line_breaks = True + if not (ch == '\n' or '\x20' <= ch <= '\x7E'): + if (ch == '\x85' or '\xA0' <= ch <= '\uD7FF' + or '\uE000' <= ch <= '\uFFFD' + or '\U00010000' <= ch < '\U0010ffff') and ch != '\uFEFF': + unicode_characters = True + if not self.allow_unicode: + special_characters = True + else: + special_characters = True + + # Detect important whitespace combinations. + if ch == ' ': + if index == 0: + leading_space = True + if index == len(scalar)-1: + trailing_space = True + if previous_break: + break_space = True + previous_space = True + previous_break = False + elif ch in '\n\x85\u2028\u2029': + if index == 0: + leading_break = True + if index == len(scalar)-1: + trailing_break = True + if previous_space: + space_break = True + previous_space = False + previous_break = True + else: + previous_space = False + previous_break = False + + # Prepare for the next character. + index += 1 + preceded_by_whitespace = (ch in '\0 \t\r\n\x85\u2028\u2029') + followed_by_whitespace = (index+1 >= len(scalar) or + scalar[index+1] in '\0 \t\r\n\x85\u2028\u2029') + + # Let's decide what styles are allowed. + allow_flow_plain = True + allow_block_plain = True + allow_single_quoted = True + allow_double_quoted = True + allow_block = True + + # Leading and trailing whitespaces are bad for plain scalars. + if (leading_space or leading_break + or trailing_space or trailing_break): + allow_flow_plain = allow_block_plain = False + + # We do not permit trailing spaces for block scalars. + if trailing_space: + allow_block = False + + # Spaces at the beginning of a new line are only acceptable for block + # scalars. + if break_space: + allow_flow_plain = allow_block_plain = allow_single_quoted = False + + # Spaces followed by breaks, as well as special character are only + # allowed for double quoted scalars. + if space_break or special_characters: + allow_flow_plain = allow_block_plain = \ + allow_single_quoted = allow_block = False + + # Although the plain scalar writer supports breaks, we never emit + # multiline plain scalars. + if line_breaks: + allow_flow_plain = allow_block_plain = False + + # Flow indicators are forbidden for flow plain scalars. + if flow_indicators: + allow_flow_plain = False + + # Block indicators are forbidden for block plain scalars. + if block_indicators: + allow_block_plain = False + + return ScalarAnalysis(scalar=scalar, + empty=False, multiline=line_breaks, + allow_flow_plain=allow_flow_plain, + allow_block_plain=allow_block_plain, + allow_single_quoted=allow_single_quoted, + allow_double_quoted=allow_double_quoted, + allow_block=allow_block) + + # Writers. + + def flush_stream(self): + if hasattr(self.stream, 'flush'): + self.stream.flush() + + def write_stream_start(self): + # Write BOM if needed. + if self.encoding and self.encoding.startswith('utf-16'): + self.stream.write('\uFEFF'.encode(self.encoding)) + + def write_stream_end(self): + self.flush_stream() + + def write_indicator(self, indicator, need_whitespace, + whitespace=False, indention=False): + if self.whitespace or not need_whitespace: + data = indicator + else: + data = ' '+indicator + self.whitespace = whitespace + self.indention = self.indention and indention + self.column += len(data) + self.open_ended = False + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + + def write_indent(self): + indent = self.indent or 0 + if not self.indention or self.column > indent \ + or (self.column == indent and not self.whitespace): + self.write_line_break() + if self.column < indent: + self.whitespace = True + data = ' '*(indent-self.column) + self.column = indent + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + + def write_line_break(self, data=None): + if data is None: + data = self.best_line_break + self.whitespace = True + self.indention = True + self.line += 1 + self.column = 0 + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + + def write_version_directive(self, version_text): + data = '%%YAML %s' % version_text + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + self.write_line_break() + + def write_tag_directive(self, handle_text, prefix_text): + data = '%%TAG %s %s' % (handle_text, prefix_text) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + self.write_line_break() + + # Scalar streams. + + def write_single_quoted(self, text, split=True): + self.write_indicator('\'', True) + spaces = False + breaks = False + start = end = 0 + while end <= len(text): + ch = None + if end < len(text): + ch = text[end] + if spaces: + if ch is None or ch != ' ': + if start+1 == end and self.column > self.best_width and split \ + and start != 0 and end != len(text): + self.write_indent() + else: + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + elif breaks: + if ch is None or ch not in '\n\x85\u2028\u2029': + if text[start] == '\n': + self.write_line_break() + for br in text[start:end]: + if br == '\n': + self.write_line_break() + else: + self.write_line_break(br) + self.write_indent() + start = end + else: + if ch is None or ch in ' \n\x85\u2028\u2029' or ch == '\'': + if start < end: + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + if ch == '\'': + data = '\'\'' + self.column += 2 + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + 1 + if ch is not None: + spaces = (ch == ' ') + breaks = (ch in '\n\x85\u2028\u2029') + end += 1 + self.write_indicator('\'', False) + + ESCAPE_REPLACEMENTS = { + '\0': '0', + '\x07': 'a', + '\x08': 'b', + '\x09': 't', + '\x0A': 'n', + '\x0B': 'v', + '\x0C': 'f', + '\x0D': 'r', + '\x1B': 'e', + '\"': '\"', + '\\': '\\', + '\x85': 'N', + '\xA0': '_', + '\u2028': 'L', + '\u2029': 'P', + } + + def write_double_quoted(self, text, split=True): + self.write_indicator('"', True) + start = end = 0 + while end <= len(text): + ch = None + if end < len(text): + ch = text[end] + if ch is None or ch in '"\\\x85\u2028\u2029\uFEFF' \ + or not ('\x20' <= ch <= '\x7E' + or (self.allow_unicode + and ('\xA0' <= ch <= '\uD7FF' + or '\uE000' <= ch <= '\uFFFD'))): + if start < end: + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + if ch is not None: + if ch in self.ESCAPE_REPLACEMENTS: + data = '\\'+self.ESCAPE_REPLACEMENTS[ch] + elif ch <= '\xFF': + data = '\\x%02X' % ord(ch) + elif ch <= '\uFFFF': + data = '\\u%04X' % ord(ch) + else: + data = '\\U%08X' % ord(ch) + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end+1 + if 0 < end < len(text)-1 and (ch == ' ' or start >= end) \ + and self.column+(end-start) > self.best_width and split: + data = text[start:end]+'\\' + if start < end: + start = end + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + self.write_indent() + self.whitespace = False + self.indention = False + if text[start] == ' ': + data = '\\' + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + end += 1 + self.write_indicator('"', False) + + def determine_block_hints(self, text): + hints = '' + if text: + if text[0] in ' \n\x85\u2028\u2029': + hints += str(self.best_indent) + if text[-1] not in '\n\x85\u2028\u2029': + hints += '-' + elif len(text) == 1 or text[-2] in '\n\x85\u2028\u2029': + hints += '+' + return hints + + def write_folded(self, text): + hints = self.determine_block_hints(text) + self.write_indicator('>'+hints, True) + if hints[-1:] == '+': + self.open_ended = True + self.write_line_break() + leading_space = True + spaces = False + breaks = True + start = end = 0 + while end <= len(text): + ch = None + if end < len(text): + ch = text[end] + if breaks: + if ch is None or ch not in '\n\x85\u2028\u2029': + if not leading_space and ch is not None and ch != ' ' \ + and text[start] == '\n': + self.write_line_break() + leading_space = (ch == ' ') + for br in text[start:end]: + if br == '\n': + self.write_line_break() + else: + self.write_line_break(br) + if ch is not None: + self.write_indent() + start = end + elif spaces: + if ch != ' ': + if start+1 == end and self.column > self.best_width: + self.write_indent() + else: + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + else: + if ch is None or ch in ' \n\x85\u2028\u2029': + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + if ch is None: + self.write_line_break() + start = end + if ch is not None: + breaks = (ch in '\n\x85\u2028\u2029') + spaces = (ch == ' ') + end += 1 + + def write_literal(self, text): + hints = self.determine_block_hints(text) + self.write_indicator('|'+hints, True) + if hints[-1:] == '+': + self.open_ended = True + self.write_line_break() + breaks = True + start = end = 0 + while end <= len(text): + ch = None + if end < len(text): + ch = text[end] + if breaks: + if ch is None or ch not in '\n\x85\u2028\u2029': + for br in text[start:end]: + if br == '\n': + self.write_line_break() + else: + self.write_line_break(br) + if ch is not None: + self.write_indent() + start = end + else: + if ch is None or ch in '\n\x85\u2028\u2029': + data = text[start:end] + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + if ch is None: + self.write_line_break() + start = end + if ch is not None: + breaks = (ch in '\n\x85\u2028\u2029') + end += 1 + + def write_plain(self, text, split=True): + if self.root_context: + self.open_ended = True + if not text: + return + if not self.whitespace: + data = ' ' + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + self.whitespace = False + self.indention = False + spaces = False + breaks = False + start = end = 0 + while end <= len(text): + ch = None + if end < len(text): + ch = text[end] + if spaces: + if ch != ' ': + if start+1 == end and self.column > self.best_width and split: + self.write_indent() + self.whitespace = False + self.indention = False + else: + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + elif breaks: + if ch not in '\n\x85\u2028\u2029': + if text[start] == '\n': + self.write_line_break() + for br in text[start:end]: + if br == '\n': + self.write_line_break() + else: + self.write_line_break(br) + self.write_indent() + self.whitespace = False + self.indention = False + start = end + else: + if ch is None or ch in ' \n\x85\u2028\u2029': + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + if ch is not None: + spaces = (ch == ' ') + breaks = (ch in '\n\x85\u2028\u2029') + end += 1 diff --git a/third_party/python/PyYAML/lib3/yaml/error.py b/third_party/python/PyYAML/lib3/yaml/error.py new file mode 100644 index 0000000000..b796b4dc51 --- /dev/null +++ b/third_party/python/PyYAML/lib3/yaml/error.py @@ -0,0 +1,75 @@ + +__all__ = ['Mark', 'YAMLError', 'MarkedYAMLError'] + +class Mark: + + def __init__(self, name, index, line, column, buffer, pointer): + self.name = name + self.index = index + self.line = line + self.column = column + self.buffer = buffer + self.pointer = pointer + + def get_snippet(self, indent=4, max_length=75): + if self.buffer is None: + return None + head = '' + start = self.pointer + while start > 0 and self.buffer[start-1] not in '\0\r\n\x85\u2028\u2029': + start -= 1 + if self.pointer-start > max_length/2-1: + head = ' ... ' + start += 5 + break + tail = '' + end = self.pointer + while end < len(self.buffer) and self.buffer[end] not in '\0\r\n\x85\u2028\u2029': + end += 1 + if end-self.pointer > max_length/2-1: + tail = ' ... ' + end -= 5 + break + snippet = self.buffer[start:end] + return ' '*indent + head + snippet + tail + '\n' \ + + ' '*(indent+self.pointer-start+len(head)) + '^' + + def __str__(self): + snippet = self.get_snippet() + where = " in \"%s\", line %d, column %d" \ + % (self.name, self.line+1, self.column+1) + if snippet is not None: + where += ":\n"+snippet + return where + +class YAMLError(Exception): + pass + +class MarkedYAMLError(YAMLError): + + def __init__(self, context=None, context_mark=None, + problem=None, problem_mark=None, note=None): + self.context = context + self.context_mark = context_mark + self.problem = problem + self.problem_mark = problem_mark + self.note = note + + def __str__(self): + lines = [] + if self.context is not None: + lines.append(self.context) + if self.context_mark is not None \ + and (self.problem is None or self.problem_mark is None + or self.context_mark.name != self.problem_mark.name + or self.context_mark.line != self.problem_mark.line + or self.context_mark.column != self.problem_mark.column): + lines.append(str(self.context_mark)) + if self.problem is not None: + lines.append(self.problem) + if self.problem_mark is not None: + lines.append(str(self.problem_mark)) + if self.note is not None: + lines.append(self.note) + return '\n'.join(lines) + diff --git a/third_party/python/PyYAML/lib3/yaml/events.py b/third_party/python/PyYAML/lib3/yaml/events.py new file mode 100644 index 0000000000..f79ad389cb --- /dev/null +++ b/third_party/python/PyYAML/lib3/yaml/events.py @@ -0,0 +1,86 @@ + +# Abstract classes. + +class Event(object): + def __init__(self, start_mark=None, end_mark=None): + self.start_mark = start_mark + self.end_mark = end_mark + def __repr__(self): + attributes = [key for key in ['anchor', 'tag', 'implicit', 'value'] + if hasattr(self, key)] + arguments = ', '.join(['%s=%r' % (key, getattr(self, key)) + for key in attributes]) + return '%s(%s)' % (self.__class__.__name__, arguments) + +class NodeEvent(Event): + def __init__(self, anchor, start_mark=None, end_mark=None): + self.anchor = anchor + self.start_mark = start_mark + self.end_mark = end_mark + +class CollectionStartEvent(NodeEvent): + def __init__(self, anchor, tag, implicit, start_mark=None, end_mark=None, + flow_style=None): + self.anchor = anchor + self.tag = tag + self.implicit = implicit + self.start_mark = start_mark + self.end_mark = end_mark + self.flow_style = flow_style + +class CollectionEndEvent(Event): + pass + +# Implementations. + +class StreamStartEvent(Event): + def __init__(self, start_mark=None, end_mark=None, encoding=None): + self.start_mark = start_mark + self.end_mark = end_mark + self.encoding = encoding + +class StreamEndEvent(Event): + pass + +class DocumentStartEvent(Event): + def __init__(self, start_mark=None, end_mark=None, + explicit=None, version=None, tags=None): + self.start_mark = start_mark + self.end_mark = end_mark + self.explicit = explicit + self.version = version + self.tags = tags + +class DocumentEndEvent(Event): + def __init__(self, start_mark=None, end_mark=None, + explicit=None): + self.start_mark = start_mark + self.end_mark = end_mark + self.explicit = explicit + +class AliasEvent(NodeEvent): + pass + +class ScalarEvent(NodeEvent): + def __init__(self, anchor, tag, implicit, value, + start_mark=None, end_mark=None, style=None): + self.anchor = anchor + self.tag = tag + self.implicit = implicit + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + self.style = style + +class SequenceStartEvent(CollectionStartEvent): + pass + +class SequenceEndEvent(CollectionEndEvent): + pass + +class MappingStartEvent(CollectionStartEvent): + pass + +class MappingEndEvent(CollectionEndEvent): + pass + diff --git a/third_party/python/PyYAML/lib3/yaml/loader.py b/third_party/python/PyYAML/lib3/yaml/loader.py new file mode 100644 index 0000000000..e90c11224c --- /dev/null +++ b/third_party/python/PyYAML/lib3/yaml/loader.py @@ -0,0 +1,63 @@ + +__all__ = ['BaseLoader', 'FullLoader', 'SafeLoader', 'Loader', 'UnsafeLoader'] + +from .reader import * +from .scanner import * +from .parser import * +from .composer import * +from .constructor import * +from .resolver import * + +class BaseLoader(Reader, Scanner, Parser, Composer, BaseConstructor, BaseResolver): + + def __init__(self, stream): + Reader.__init__(self, stream) + Scanner.__init__(self) + Parser.__init__(self) + Composer.__init__(self) + BaseConstructor.__init__(self) + BaseResolver.__init__(self) + +class FullLoader(Reader, Scanner, Parser, Composer, FullConstructor, Resolver): + + def __init__(self, stream): + Reader.__init__(self, stream) + Scanner.__init__(self) + Parser.__init__(self) + Composer.__init__(self) + FullConstructor.__init__(self) + Resolver.__init__(self) + +class SafeLoader(Reader, Scanner, Parser, Composer, SafeConstructor, Resolver): + + def __init__(self, stream): + Reader.__init__(self, stream) + Scanner.__init__(self) + Parser.__init__(self) + Composer.__init__(self) + SafeConstructor.__init__(self) + Resolver.__init__(self) + +class Loader(Reader, Scanner, Parser, Composer, Constructor, Resolver): + + def __init__(self, stream): + Reader.__init__(self, stream) + Scanner.__init__(self) + Parser.__init__(self) + Composer.__init__(self) + Constructor.__init__(self) + Resolver.__init__(self) + +# UnsafeLoader is the same as Loader (which is and was always unsafe on +# untrusted input). Use of either Loader or UnsafeLoader should be rare, since +# FullLoad should be able to load almost all YAML safely. Loader is left intact +# to ensure backwards compatibility. +class UnsafeLoader(Reader, Scanner, Parser, Composer, Constructor, Resolver): + + def __init__(self, stream): + Reader.__init__(self, stream) + Scanner.__init__(self) + Parser.__init__(self) + Composer.__init__(self) + Constructor.__init__(self) + Resolver.__init__(self) diff --git a/third_party/python/PyYAML/lib3/yaml/nodes.py b/third_party/python/PyYAML/lib3/yaml/nodes.py new file mode 100644 index 0000000000..c4f070c41e --- /dev/null +++ b/third_party/python/PyYAML/lib3/yaml/nodes.py @@ -0,0 +1,49 @@ + +class Node(object): + def __init__(self, tag, value, start_mark, end_mark): + self.tag = tag + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + def __repr__(self): + value = self.value + #if isinstance(value, list): + # if len(value) == 0: + # value = '' + # elif len(value) == 1: + # value = '<1 item>' + # else: + # value = '<%d items>' % len(value) + #else: + # if len(value) > 75: + # value = repr(value[:70]+u' ... ') + # else: + # value = repr(value) + value = repr(value) + return '%s(tag=%r, value=%s)' % (self.__class__.__name__, self.tag, value) + +class ScalarNode(Node): + id = 'scalar' + def __init__(self, tag, value, + start_mark=None, end_mark=None, style=None): + self.tag = tag + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + self.style = style + +class CollectionNode(Node): + def __init__(self, tag, value, + start_mark=None, end_mark=None, flow_style=None): + self.tag = tag + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + self.flow_style = flow_style + +class SequenceNode(CollectionNode): + id = 'sequence' + +class MappingNode(CollectionNode): + id = 'mapping' + diff --git a/third_party/python/PyYAML/lib3/yaml/parser.py b/third_party/python/PyYAML/lib3/yaml/parser.py new file mode 100644 index 0000000000..13a5995d29 --- /dev/null +++ b/third_party/python/PyYAML/lib3/yaml/parser.py @@ -0,0 +1,589 @@ + +# The following YAML grammar is LL(1) and is parsed by a recursive descent +# parser. +# +# stream ::= STREAM-START implicit_document? explicit_document* STREAM-END +# implicit_document ::= block_node DOCUMENT-END* +# explicit_document ::= DIRECTIVE* DOCUMENT-START block_node? DOCUMENT-END* +# block_node_or_indentless_sequence ::= +# ALIAS +# | properties (block_content | indentless_block_sequence)? +# | block_content +# | indentless_block_sequence +# block_node ::= ALIAS +# | properties block_content? +# | block_content +# flow_node ::= ALIAS +# | properties flow_content? +# | flow_content +# properties ::= TAG ANCHOR? | ANCHOR TAG? +# block_content ::= block_collection | flow_collection | SCALAR +# flow_content ::= flow_collection | SCALAR +# block_collection ::= block_sequence | block_mapping +# flow_collection ::= flow_sequence | flow_mapping +# block_sequence ::= BLOCK-SEQUENCE-START (BLOCK-ENTRY block_node?)* BLOCK-END +# indentless_sequence ::= (BLOCK-ENTRY block_node?)+ +# block_mapping ::= BLOCK-MAPPING_START +# ((KEY block_node_or_indentless_sequence?)? +# (VALUE block_node_or_indentless_sequence?)?)* +# BLOCK-END +# flow_sequence ::= FLOW-SEQUENCE-START +# (flow_sequence_entry FLOW-ENTRY)* +# flow_sequence_entry? +# FLOW-SEQUENCE-END +# flow_sequence_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? +# flow_mapping ::= FLOW-MAPPING-START +# (flow_mapping_entry FLOW-ENTRY)* +# flow_mapping_entry? +# FLOW-MAPPING-END +# flow_mapping_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? +# +# FIRST sets: +# +# stream: { STREAM-START } +# explicit_document: { DIRECTIVE DOCUMENT-START } +# implicit_document: FIRST(block_node) +# block_node: { ALIAS TAG ANCHOR SCALAR BLOCK-SEQUENCE-START BLOCK-MAPPING-START FLOW-SEQUENCE-START FLOW-MAPPING-START } +# flow_node: { ALIAS ANCHOR TAG SCALAR FLOW-SEQUENCE-START FLOW-MAPPING-START } +# block_content: { BLOCK-SEQUENCE-START BLOCK-MAPPING-START FLOW-SEQUENCE-START FLOW-MAPPING-START SCALAR } +# flow_content: { FLOW-SEQUENCE-START FLOW-MAPPING-START SCALAR } +# block_collection: { BLOCK-SEQUENCE-START BLOCK-MAPPING-START } +# flow_collection: { FLOW-SEQUENCE-START FLOW-MAPPING-START } +# block_sequence: { BLOCK-SEQUENCE-START } +# block_mapping: { BLOCK-MAPPING-START } +# block_node_or_indentless_sequence: { ALIAS ANCHOR TAG SCALAR BLOCK-SEQUENCE-START BLOCK-MAPPING-START FLOW-SEQUENCE-START FLOW-MAPPING-START BLOCK-ENTRY } +# indentless_sequence: { ENTRY } +# flow_collection: { FLOW-SEQUENCE-START FLOW-MAPPING-START } +# flow_sequence: { FLOW-SEQUENCE-START } +# flow_mapping: { FLOW-MAPPING-START } +# flow_sequence_entry: { ALIAS ANCHOR TAG SCALAR FLOW-SEQUENCE-START FLOW-MAPPING-START KEY } +# flow_mapping_entry: { ALIAS ANCHOR TAG SCALAR FLOW-SEQUENCE-START FLOW-MAPPING-START KEY } + +__all__ = ['Parser', 'ParserError'] + +from .error import MarkedYAMLError +from .tokens import * +from .events import * +from .scanner import * + +class ParserError(MarkedYAMLError): + pass + +class Parser: + # Since writing a recursive-descendant parser is a straightforward task, we + # do not give many comments here. + + DEFAULT_TAGS = { + '!': '!', + '!!': 'tag:yaml.org,2002:', + } + + def __init__(self): + self.current_event = None + self.yaml_version = None + self.tag_handles = {} + self.states = [] + self.marks = [] + self.state = self.parse_stream_start + + def dispose(self): + # Reset the state attributes (to clear self-references) + self.states = [] + self.state = None + + def check_event(self, *choices): + # Check the type of the next event. + if self.current_event is None: + if self.state: + self.current_event = self.state() + if self.current_event is not None: + if not choices: + return True + for choice in choices: + if isinstance(self.current_event, choice): + return True + return False + + def peek_event(self): + # Get the next event. + if self.current_event is None: + if self.state: + self.current_event = self.state() + return self.current_event + + def get_event(self): + # Get the next event and proceed further. + if self.current_event is None: + if self.state: + self.current_event = self.state() + value = self.current_event + self.current_event = None + return value + + # stream ::= STREAM-START implicit_document? explicit_document* STREAM-END + # implicit_document ::= block_node DOCUMENT-END* + # explicit_document ::= DIRECTIVE* DOCUMENT-START block_node? DOCUMENT-END* + + def parse_stream_start(self): + + # Parse the stream start. + token = self.get_token() + event = StreamStartEvent(token.start_mark, token.end_mark, + encoding=token.encoding) + + # Prepare the next state. + self.state = self.parse_implicit_document_start + + return event + + def parse_implicit_document_start(self): + + # Parse an implicit document. + if not self.check_token(DirectiveToken, DocumentStartToken, + StreamEndToken): + self.tag_handles = self.DEFAULT_TAGS + token = self.peek_token() + start_mark = end_mark = token.start_mark + event = DocumentStartEvent(start_mark, end_mark, + explicit=False) + + # Prepare the next state. + self.states.append(self.parse_document_end) + self.state = self.parse_block_node + + return event + + else: + return self.parse_document_start() + + def parse_document_start(self): + + # Parse any extra document end indicators. + while self.check_token(DocumentEndToken): + self.get_token() + + # Parse an explicit document. + if not self.check_token(StreamEndToken): + token = self.peek_token() + start_mark = token.start_mark + version, tags = self.process_directives() + if not self.check_token(DocumentStartToken): + raise ParserError(None, None, + "expected '', but found %r" + % self.peek_token().id, + self.peek_token().start_mark) + token = self.get_token() + end_mark = token.end_mark + event = DocumentStartEvent(start_mark, end_mark, + explicit=True, version=version, tags=tags) + self.states.append(self.parse_document_end) + self.state = self.parse_document_content + else: + # Parse the end of the stream. + token = self.get_token() + event = StreamEndEvent(token.start_mark, token.end_mark) + assert not self.states + assert not self.marks + self.state = None + return event + + def parse_document_end(self): + + # Parse the document end. + token = self.peek_token() + start_mark = end_mark = token.start_mark + explicit = False + if self.check_token(DocumentEndToken): + token = self.get_token() + end_mark = token.end_mark + explicit = True + event = DocumentEndEvent(start_mark, end_mark, + explicit=explicit) + + # Prepare the next state. + self.state = self.parse_document_start + + return event + + def parse_document_content(self): + if self.check_token(DirectiveToken, + DocumentStartToken, DocumentEndToken, StreamEndToken): + event = self.process_empty_scalar(self.peek_token().start_mark) + self.state = self.states.pop() + return event + else: + return self.parse_block_node() + + def process_directives(self): + self.yaml_version = None + self.tag_handles = {} + while self.check_token(DirectiveToken): + token = self.get_token() + if token.name == 'YAML': + if self.yaml_version is not None: + raise ParserError(None, None, + "found duplicate YAML directive", token.start_mark) + major, minor = token.value + if major != 1: + raise ParserError(None, None, + "found incompatible YAML document (version 1.* is required)", + token.start_mark) + self.yaml_version = token.value + elif token.name == 'TAG': + handle, prefix = token.value + if handle in self.tag_handles: + raise ParserError(None, None, + "duplicate tag handle %r" % handle, + token.start_mark) + self.tag_handles[handle] = prefix + if self.tag_handles: + value = self.yaml_version, self.tag_handles.copy() + else: + value = self.yaml_version, None + for key in self.DEFAULT_TAGS: + if key not in self.tag_handles: + self.tag_handles[key] = self.DEFAULT_TAGS[key] + return value + + # block_node_or_indentless_sequence ::= ALIAS + # | properties (block_content | indentless_block_sequence)? + # | block_content + # | indentless_block_sequence + # block_node ::= ALIAS + # | properties block_content? + # | block_content + # flow_node ::= ALIAS + # | properties flow_content? + # | flow_content + # properties ::= TAG ANCHOR? | ANCHOR TAG? + # block_content ::= block_collection | flow_collection | SCALAR + # flow_content ::= flow_collection | SCALAR + # block_collection ::= block_sequence | block_mapping + # flow_collection ::= flow_sequence | flow_mapping + + def parse_block_node(self): + return self.parse_node(block=True) + + def parse_flow_node(self): + return self.parse_node() + + def parse_block_node_or_indentless_sequence(self): + return self.parse_node(block=True, indentless_sequence=True) + + def parse_node(self, block=False, indentless_sequence=False): + if self.check_token(AliasToken): + token = self.get_token() + event = AliasEvent(token.value, token.start_mark, token.end_mark) + self.state = self.states.pop() + else: + anchor = None + tag = None + start_mark = end_mark = tag_mark = None + if self.check_token(AnchorToken): + token = self.get_token() + start_mark = token.start_mark + end_mark = token.end_mark + anchor = token.value + if self.check_token(TagToken): + token = self.get_token() + tag_mark = token.start_mark + end_mark = token.end_mark + tag = token.value + elif self.check_token(TagToken): + token = self.get_token() + start_mark = tag_mark = token.start_mark + end_mark = token.end_mark + tag = token.value + if self.check_token(AnchorToken): + token = self.get_token() + end_mark = token.end_mark + anchor = token.value + if tag is not None: + handle, suffix = tag + if handle is not None: + if handle not in self.tag_handles: + raise ParserError("while parsing a node", start_mark, + "found undefined tag handle %r" % handle, + tag_mark) + tag = self.tag_handles[handle]+suffix + else: + tag = suffix + #if tag == '!': + # raise ParserError("while parsing a node", start_mark, + # "found non-specific tag '!'", tag_mark, + # "Please check 'http://pyyaml.org/wiki/YAMLNonSpecificTag' and share your opinion.") + if start_mark is None: + start_mark = end_mark = self.peek_token().start_mark + event = None + implicit = (tag is None or tag == '!') + if indentless_sequence and self.check_token(BlockEntryToken): + end_mark = self.peek_token().end_mark + event = SequenceStartEvent(anchor, tag, implicit, + start_mark, end_mark) + self.state = self.parse_indentless_sequence_entry + else: + if self.check_token(ScalarToken): + token = self.get_token() + end_mark = token.end_mark + if (token.plain and tag is None) or tag == '!': + implicit = (True, False) + elif tag is None: + implicit = (False, True) + else: + implicit = (False, False) + event = ScalarEvent(anchor, tag, implicit, token.value, + start_mark, end_mark, style=token.style) + self.state = self.states.pop() + elif self.check_token(FlowSequenceStartToken): + end_mark = self.peek_token().end_mark + event = SequenceStartEvent(anchor, tag, implicit, + start_mark, end_mark, flow_style=True) + self.state = self.parse_flow_sequence_first_entry + elif self.check_token(FlowMappingStartToken): + end_mark = self.peek_token().end_mark + event = MappingStartEvent(anchor, tag, implicit, + start_mark, end_mark, flow_style=True) + self.state = self.parse_flow_mapping_first_key + elif block and self.check_token(BlockSequenceStartToken): + end_mark = self.peek_token().start_mark + event = SequenceStartEvent(anchor, tag, implicit, + start_mark, end_mark, flow_style=False) + self.state = self.parse_block_sequence_first_entry + elif block and self.check_token(BlockMappingStartToken): + end_mark = self.peek_token().start_mark + event = MappingStartEvent(anchor, tag, implicit, + start_mark, end_mark, flow_style=False) + self.state = self.parse_block_mapping_first_key + elif anchor is not None or tag is not None: + # Empty scalars are allowed even if a tag or an anchor is + # specified. + event = ScalarEvent(anchor, tag, (implicit, False), '', + start_mark, end_mark) + self.state = self.states.pop() + else: + if block: + node = 'block' + else: + node = 'flow' + token = self.peek_token() + raise ParserError("while parsing a %s node" % node, start_mark, + "expected the node content, but found %r" % token.id, + token.start_mark) + return event + + # block_sequence ::= BLOCK-SEQUENCE-START (BLOCK-ENTRY block_node?)* BLOCK-END + + def parse_block_sequence_first_entry(self): + token = self.get_token() + self.marks.append(token.start_mark) + return self.parse_block_sequence_entry() + + def parse_block_sequence_entry(self): + if self.check_token(BlockEntryToken): + token = self.get_token() + if not self.check_token(BlockEntryToken, BlockEndToken): + self.states.append(self.parse_block_sequence_entry) + return self.parse_block_node() + else: + self.state = self.parse_block_sequence_entry + return self.process_empty_scalar(token.end_mark) + if not self.check_token(BlockEndToken): + token = self.peek_token() + raise ParserError("while parsing a block collection", self.marks[-1], + "expected , but found %r" % token.id, token.start_mark) + token = self.get_token() + event = SequenceEndEvent(token.start_mark, token.end_mark) + self.state = self.states.pop() + self.marks.pop() + return event + + # indentless_sequence ::= (BLOCK-ENTRY block_node?)+ + + def parse_indentless_sequence_entry(self): + if self.check_token(BlockEntryToken): + token = self.get_token() + if not self.check_token(BlockEntryToken, + KeyToken, ValueToken, BlockEndToken): + self.states.append(self.parse_indentless_sequence_entry) + return self.parse_block_node() + else: + self.state = self.parse_indentless_sequence_entry + return self.process_empty_scalar(token.end_mark) + token = self.peek_token() + event = SequenceEndEvent(token.start_mark, token.start_mark) + self.state = self.states.pop() + return event + + # block_mapping ::= BLOCK-MAPPING_START + # ((KEY block_node_or_indentless_sequence?)? + # (VALUE block_node_or_indentless_sequence?)?)* + # BLOCK-END + + def parse_block_mapping_first_key(self): + token = self.get_token() + self.marks.append(token.start_mark) + return self.parse_block_mapping_key() + + def parse_block_mapping_key(self): + if self.check_token(KeyToken): + token = self.get_token() + if not self.check_token(KeyToken, ValueToken, BlockEndToken): + self.states.append(self.parse_block_mapping_value) + return self.parse_block_node_or_indentless_sequence() + else: + self.state = self.parse_block_mapping_value + return self.process_empty_scalar(token.end_mark) + if not self.check_token(BlockEndToken): + token = self.peek_token() + raise ParserError("while parsing a block mapping", self.marks[-1], + "expected , but found %r" % token.id, token.start_mark) + token = self.get_token() + event = MappingEndEvent(token.start_mark, token.end_mark) + self.state = self.states.pop() + self.marks.pop() + return event + + def parse_block_mapping_value(self): + if self.check_token(ValueToken): + token = self.get_token() + if not self.check_token(KeyToken, ValueToken, BlockEndToken): + self.states.append(self.parse_block_mapping_key) + return self.parse_block_node_or_indentless_sequence() + else: + self.state = self.parse_block_mapping_key + return self.process_empty_scalar(token.end_mark) + else: + self.state = self.parse_block_mapping_key + token = self.peek_token() + return self.process_empty_scalar(token.start_mark) + + # flow_sequence ::= FLOW-SEQUENCE-START + # (flow_sequence_entry FLOW-ENTRY)* + # flow_sequence_entry? + # FLOW-SEQUENCE-END + # flow_sequence_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? + # + # Note that while production rules for both flow_sequence_entry and + # flow_mapping_entry are equal, their interpretations are different. + # For `flow_sequence_entry`, the part `KEY flow_node? (VALUE flow_node?)?` + # generate an inline mapping (set syntax). + + def parse_flow_sequence_first_entry(self): + token = self.get_token() + self.marks.append(token.start_mark) + return self.parse_flow_sequence_entry(first=True) + + def parse_flow_sequence_entry(self, first=False): + if not self.check_token(FlowSequenceEndToken): + if not first: + if self.check_token(FlowEntryToken): + self.get_token() + else: + token = self.peek_token() + raise ParserError("while parsing a flow sequence", self.marks[-1], + "expected ',' or ']', but got %r" % token.id, token.start_mark) + + if self.check_token(KeyToken): + token = self.peek_token() + event = MappingStartEvent(None, None, True, + token.start_mark, token.end_mark, + flow_style=True) + self.state = self.parse_flow_sequence_entry_mapping_key + return event + elif not self.check_token(FlowSequenceEndToken): + self.states.append(self.parse_flow_sequence_entry) + return self.parse_flow_node() + token = self.get_token() + event = SequenceEndEvent(token.start_mark, token.end_mark) + self.state = self.states.pop() + self.marks.pop() + return event + + def parse_flow_sequence_entry_mapping_key(self): + token = self.get_token() + if not self.check_token(ValueToken, + FlowEntryToken, FlowSequenceEndToken): + self.states.append(self.parse_flow_sequence_entry_mapping_value) + return self.parse_flow_node() + else: + self.state = self.parse_flow_sequence_entry_mapping_value + return self.process_empty_scalar(token.end_mark) + + def parse_flow_sequence_entry_mapping_value(self): + if self.check_token(ValueToken): + token = self.get_token() + if not self.check_token(FlowEntryToken, FlowSequenceEndToken): + self.states.append(self.parse_flow_sequence_entry_mapping_end) + return self.parse_flow_node() + else: + self.state = self.parse_flow_sequence_entry_mapping_end + return self.process_empty_scalar(token.end_mark) + else: + self.state = self.parse_flow_sequence_entry_mapping_end + token = self.peek_token() + return self.process_empty_scalar(token.start_mark) + + def parse_flow_sequence_entry_mapping_end(self): + self.state = self.parse_flow_sequence_entry + token = self.peek_token() + return MappingEndEvent(token.start_mark, token.start_mark) + + # flow_mapping ::= FLOW-MAPPING-START + # (flow_mapping_entry FLOW-ENTRY)* + # flow_mapping_entry? + # FLOW-MAPPING-END + # flow_mapping_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? + + def parse_flow_mapping_first_key(self): + token = self.get_token() + self.marks.append(token.start_mark) + return self.parse_flow_mapping_key(first=True) + + def parse_flow_mapping_key(self, first=False): + if not self.check_token(FlowMappingEndToken): + if not first: + if self.check_token(FlowEntryToken): + self.get_token() + else: + token = self.peek_token() + raise ParserError("while parsing a flow mapping", self.marks[-1], + "expected ',' or '}', but got %r" % token.id, token.start_mark) + if self.check_token(KeyToken): + token = self.get_token() + if not self.check_token(ValueToken, + FlowEntryToken, FlowMappingEndToken): + self.states.append(self.parse_flow_mapping_value) + return self.parse_flow_node() + else: + self.state = self.parse_flow_mapping_value + return self.process_empty_scalar(token.end_mark) + elif not self.check_token(FlowMappingEndToken): + self.states.append(self.parse_flow_mapping_empty_value) + return self.parse_flow_node() + token = self.get_token() + event = MappingEndEvent(token.start_mark, token.end_mark) + self.state = self.states.pop() + self.marks.pop() + return event + + def parse_flow_mapping_value(self): + if self.check_token(ValueToken): + token = self.get_token() + if not self.check_token(FlowEntryToken, FlowMappingEndToken): + self.states.append(self.parse_flow_mapping_key) + return self.parse_flow_node() + else: + self.state = self.parse_flow_mapping_key + return self.process_empty_scalar(token.end_mark) + else: + self.state = self.parse_flow_mapping_key + token = self.peek_token() + return self.process_empty_scalar(token.start_mark) + + def parse_flow_mapping_empty_value(self): + self.state = self.parse_flow_mapping_key + return self.process_empty_scalar(self.peek_token().start_mark) + + def process_empty_scalar(self, mark): + return ScalarEvent(None, None, (True, False), '', mark, mark) + diff --git a/third_party/python/PyYAML/lib3/yaml/reader.py b/third_party/python/PyYAML/lib3/yaml/reader.py new file mode 100644 index 0000000000..774b0219b5 --- /dev/null +++ b/third_party/python/PyYAML/lib3/yaml/reader.py @@ -0,0 +1,185 @@ +# This module contains abstractions for the input stream. You don't have to +# looks further, there are no pretty code. +# +# We define two classes here. +# +# Mark(source, line, column) +# It's just a record and its only use is producing nice error messages. +# Parser does not use it for any other purposes. +# +# Reader(source, data) +# Reader determines the encoding of `data` and converts it to unicode. +# Reader provides the following methods and attributes: +# reader.peek(length=1) - return the next `length` characters +# reader.forward(length=1) - move the current position to `length` characters. +# reader.index - the number of the current character. +# reader.line, stream.column - the line and the column of the current character. + +__all__ = ['Reader', 'ReaderError'] + +from .error import YAMLError, Mark + +import codecs, re + +class ReaderError(YAMLError): + + def __init__(self, name, position, character, encoding, reason): + self.name = name + self.character = character + self.position = position + self.encoding = encoding + self.reason = reason + + def __str__(self): + if isinstance(self.character, bytes): + return "'%s' codec can't decode byte #x%02x: %s\n" \ + " in \"%s\", position %d" \ + % (self.encoding, ord(self.character), self.reason, + self.name, self.position) + else: + return "unacceptable character #x%04x: %s\n" \ + " in \"%s\", position %d" \ + % (self.character, self.reason, + self.name, self.position) + +class Reader(object): + # Reader: + # - determines the data encoding and converts it to a unicode string, + # - checks if characters are in allowed range, + # - adds '\0' to the end. + + # Reader accepts + # - a `bytes` object, + # - a `str` object, + # - a file-like object with its `read` method returning `str`, + # - a file-like object with its `read` method returning `unicode`. + + # Yeah, it's ugly and slow. + + def __init__(self, stream): + self.name = None + self.stream = None + self.stream_pointer = 0 + self.eof = True + self.buffer = '' + self.pointer = 0 + self.raw_buffer = None + self.raw_decode = None + self.encoding = None + self.index = 0 + self.line = 0 + self.column = 0 + if isinstance(stream, str): + self.name = "" + self.check_printable(stream) + self.buffer = stream+'\0' + elif isinstance(stream, bytes): + self.name = "" + self.raw_buffer = stream + self.determine_encoding() + else: + self.stream = stream + self.name = getattr(stream, 'name', "") + self.eof = False + self.raw_buffer = None + self.determine_encoding() + + def peek(self, index=0): + try: + return self.buffer[self.pointer+index] + except IndexError: + self.update(index+1) + return self.buffer[self.pointer+index] + + def prefix(self, length=1): + if self.pointer+length >= len(self.buffer): + self.update(length) + return self.buffer[self.pointer:self.pointer+length] + + def forward(self, length=1): + if self.pointer+length+1 >= len(self.buffer): + self.update(length+1) + while length: + ch = self.buffer[self.pointer] + self.pointer += 1 + self.index += 1 + if ch in '\n\x85\u2028\u2029' \ + or (ch == '\r' and self.buffer[self.pointer] != '\n'): + self.line += 1 + self.column = 0 + elif ch != '\uFEFF': + self.column += 1 + length -= 1 + + def get_mark(self): + if self.stream is None: + return Mark(self.name, self.index, self.line, self.column, + self.buffer, self.pointer) + else: + return Mark(self.name, self.index, self.line, self.column, + None, None) + + def determine_encoding(self): + while not self.eof and (self.raw_buffer is None or len(self.raw_buffer) < 2): + self.update_raw() + if isinstance(self.raw_buffer, bytes): + if self.raw_buffer.startswith(codecs.BOM_UTF16_LE): + self.raw_decode = codecs.utf_16_le_decode + self.encoding = 'utf-16-le' + elif self.raw_buffer.startswith(codecs.BOM_UTF16_BE): + self.raw_decode = codecs.utf_16_be_decode + self.encoding = 'utf-16-be' + else: + self.raw_decode = codecs.utf_8_decode + self.encoding = 'utf-8' + self.update(1) + + NON_PRINTABLE = re.compile('[^\x09\x0A\x0D\x20-\x7E\x85\xA0-\uD7FF\uE000-\uFFFD\U00010000-\U0010ffff]') + def check_printable(self, data): + match = self.NON_PRINTABLE.search(data) + if match: + character = match.group() + position = self.index+(len(self.buffer)-self.pointer)+match.start() + raise ReaderError(self.name, position, ord(character), + 'unicode', "special characters are not allowed") + + def update(self, length): + if self.raw_buffer is None: + return + self.buffer = self.buffer[self.pointer:] + self.pointer = 0 + while len(self.buffer) < length: + if not self.eof: + self.update_raw() + if self.raw_decode is not None: + try: + data, converted = self.raw_decode(self.raw_buffer, + 'strict', self.eof) + except UnicodeDecodeError as exc: + character = self.raw_buffer[exc.start] + if self.stream is not None: + position = self.stream_pointer-len(self.raw_buffer)+exc.start + else: + position = exc.start + raise ReaderError(self.name, position, character, + exc.encoding, exc.reason) + else: + data = self.raw_buffer + converted = len(data) + self.check_printable(data) + self.buffer += data + self.raw_buffer = self.raw_buffer[converted:] + if self.eof: + self.buffer += '\0' + self.raw_buffer = None + break + + def update_raw(self, size=4096): + data = self.stream.read(size) + if self.raw_buffer is None: + self.raw_buffer = data + else: + self.raw_buffer += data + self.stream_pointer += len(data) + if not data: + self.eof = True diff --git a/third_party/python/PyYAML/lib3/yaml/representer.py b/third_party/python/PyYAML/lib3/yaml/representer.py new file mode 100644 index 0000000000..3b0b192ef3 --- /dev/null +++ b/third_party/python/PyYAML/lib3/yaml/representer.py @@ -0,0 +1,389 @@ + +__all__ = ['BaseRepresenter', 'SafeRepresenter', 'Representer', + 'RepresenterError'] + +from .error import * +from .nodes import * + +import datetime, copyreg, types, base64, collections + +class RepresenterError(YAMLError): + pass + +class BaseRepresenter: + + yaml_representers = {} + yaml_multi_representers = {} + + def __init__(self, default_style=None, default_flow_style=False, sort_keys=True): + self.default_style = default_style + self.sort_keys = sort_keys + self.default_flow_style = default_flow_style + self.represented_objects = {} + self.object_keeper = [] + self.alias_key = None + + def represent(self, data): + node = self.represent_data(data) + self.serialize(node) + self.represented_objects = {} + self.object_keeper = [] + self.alias_key = None + + def represent_data(self, data): + if self.ignore_aliases(data): + self.alias_key = None + else: + self.alias_key = id(data) + if self.alias_key is not None: + if self.alias_key in self.represented_objects: + node = self.represented_objects[self.alias_key] + #if node is None: + # raise RepresenterError("recursive objects are not allowed: %r" % data) + return node + #self.represented_objects[alias_key] = None + self.object_keeper.append(data) + data_types = type(data).__mro__ + if data_types[0] in self.yaml_representers: + node = self.yaml_representers[data_types[0]](self, data) + else: + for data_type in data_types: + if data_type in self.yaml_multi_representers: + node = self.yaml_multi_representers[data_type](self, data) + break + else: + if None in self.yaml_multi_representers: + node = self.yaml_multi_representers[None](self, data) + elif None in self.yaml_representers: + node = self.yaml_representers[None](self, data) + else: + node = ScalarNode(None, str(data)) + #if alias_key is not None: + # self.represented_objects[alias_key] = node + return node + + @classmethod + def add_representer(cls, data_type, representer): + if not 'yaml_representers' in cls.__dict__: + cls.yaml_representers = cls.yaml_representers.copy() + cls.yaml_representers[data_type] = representer + + @classmethod + def add_multi_representer(cls, data_type, representer): + if not 'yaml_multi_representers' in cls.__dict__: + cls.yaml_multi_representers = cls.yaml_multi_representers.copy() + cls.yaml_multi_representers[data_type] = representer + + def represent_scalar(self, tag, value, style=None): + if style is None: + style = self.default_style + node = ScalarNode(tag, value, style=style) + if self.alias_key is not None: + self.represented_objects[self.alias_key] = node + return node + + def represent_sequence(self, tag, sequence, flow_style=None): + value = [] + node = SequenceNode(tag, value, flow_style=flow_style) + if self.alias_key is not None: + self.represented_objects[self.alias_key] = node + best_style = True + for item in sequence: + node_item = self.represent_data(item) + if not (isinstance(node_item, ScalarNode) and not node_item.style): + best_style = False + value.append(node_item) + if flow_style is None: + if self.default_flow_style is not None: + node.flow_style = self.default_flow_style + else: + node.flow_style = best_style + return node + + def represent_mapping(self, tag, mapping, flow_style=None): + value = [] + node = MappingNode(tag, value, flow_style=flow_style) + if self.alias_key is not None: + self.represented_objects[self.alias_key] = node + best_style = True + if hasattr(mapping, 'items'): + mapping = list(mapping.items()) + if self.sort_keys: + try: + mapping = sorted(mapping) + except TypeError: + pass + for item_key, item_value in mapping: + node_key = self.represent_data(item_key) + node_value = self.represent_data(item_value) + if not (isinstance(node_key, ScalarNode) and not node_key.style): + best_style = False + if not (isinstance(node_value, ScalarNode) and not node_value.style): + best_style = False + value.append((node_key, node_value)) + if flow_style is None: + if self.default_flow_style is not None: + node.flow_style = self.default_flow_style + else: + node.flow_style = best_style + return node + + def ignore_aliases(self, data): + return False + +class SafeRepresenter(BaseRepresenter): + + def ignore_aliases(self, data): + if data is None: + return True + if isinstance(data, tuple) and data == (): + return True + if isinstance(data, (str, bytes, bool, int, float)): + return True + + def represent_none(self, data): + return self.represent_scalar('tag:yaml.org,2002:null', 'null') + + def represent_str(self, data): + return self.represent_scalar('tag:yaml.org,2002:str', data) + + def represent_binary(self, data): + if hasattr(base64, 'encodebytes'): + data = base64.encodebytes(data).decode('ascii') + else: + data = base64.encodestring(data).decode('ascii') + return self.represent_scalar('tag:yaml.org,2002:binary', data, style='|') + + def represent_bool(self, data): + if data: + value = 'true' + else: + value = 'false' + return self.represent_scalar('tag:yaml.org,2002:bool', value) + + def represent_int(self, data): + return self.represent_scalar('tag:yaml.org,2002:int', str(data)) + + inf_value = 1e300 + while repr(inf_value) != repr(inf_value*inf_value): + inf_value *= inf_value + + def represent_float(self, data): + if data != data or (data == 0.0 and data == 1.0): + value = '.nan' + elif data == self.inf_value: + value = '.inf' + elif data == -self.inf_value: + value = '-.inf' + else: + value = repr(data).lower() + # Note that in some cases `repr(data)` represents a float number + # without the decimal parts. For instance: + # >>> repr(1e17) + # '1e17' + # Unfortunately, this is not a valid float representation according + # to the definition of the `!!float` tag. We fix this by adding + # '.0' before the 'e' symbol. + if '.' not in value and 'e' in value: + value = value.replace('e', '.0e', 1) + return self.represent_scalar('tag:yaml.org,2002:float', value) + + def represent_list(self, data): + #pairs = (len(data) > 0 and isinstance(data, list)) + #if pairs: + # for item in data: + # if not isinstance(item, tuple) or len(item) != 2: + # pairs = False + # break + #if not pairs: + return self.represent_sequence('tag:yaml.org,2002:seq', data) + #value = [] + #for item_key, item_value in data: + # value.append(self.represent_mapping(u'tag:yaml.org,2002:map', + # [(item_key, item_value)])) + #return SequenceNode(u'tag:yaml.org,2002:pairs', value) + + def represent_dict(self, data): + return self.represent_mapping('tag:yaml.org,2002:map', data) + + def represent_set(self, data): + value = {} + for key in data: + value[key] = None + return self.represent_mapping('tag:yaml.org,2002:set', value) + + def represent_date(self, data): + value = data.isoformat() + return self.represent_scalar('tag:yaml.org,2002:timestamp', value) + + def represent_datetime(self, data): + value = data.isoformat(' ') + return self.represent_scalar('tag:yaml.org,2002:timestamp', value) + + def represent_yaml_object(self, tag, data, cls, flow_style=None): + if hasattr(data, '__getstate__'): + state = data.__getstate__() + else: + state = data.__dict__.copy() + return self.represent_mapping(tag, state, flow_style=flow_style) + + def represent_undefined(self, data): + raise RepresenterError("cannot represent an object", data) + +SafeRepresenter.add_representer(type(None), + SafeRepresenter.represent_none) + +SafeRepresenter.add_representer(str, + SafeRepresenter.represent_str) + +SafeRepresenter.add_representer(bytes, + SafeRepresenter.represent_binary) + +SafeRepresenter.add_representer(bool, + SafeRepresenter.represent_bool) + +SafeRepresenter.add_representer(int, + SafeRepresenter.represent_int) + +SafeRepresenter.add_representer(float, + SafeRepresenter.represent_float) + +SafeRepresenter.add_representer(list, + SafeRepresenter.represent_list) + +SafeRepresenter.add_representer(tuple, + SafeRepresenter.represent_list) + +SafeRepresenter.add_representer(dict, + SafeRepresenter.represent_dict) + +SafeRepresenter.add_representer(set, + SafeRepresenter.represent_set) + +SafeRepresenter.add_representer(datetime.date, + SafeRepresenter.represent_date) + +SafeRepresenter.add_representer(datetime.datetime, + SafeRepresenter.represent_datetime) + +SafeRepresenter.add_representer(None, + SafeRepresenter.represent_undefined) + +class Representer(SafeRepresenter): + + def represent_complex(self, data): + if data.imag == 0.0: + data = '%r' % data.real + elif data.real == 0.0: + data = '%rj' % data.imag + elif data.imag > 0: + data = '%r+%rj' % (data.real, data.imag) + else: + data = '%r%rj' % (data.real, data.imag) + return self.represent_scalar('tag:yaml.org,2002:python/complex', data) + + def represent_tuple(self, data): + return self.represent_sequence('tag:yaml.org,2002:python/tuple', data) + + def represent_name(self, data): + name = '%s.%s' % (data.__module__, data.__name__) + return self.represent_scalar('tag:yaml.org,2002:python/name:'+name, '') + + def represent_module(self, data): + return self.represent_scalar( + 'tag:yaml.org,2002:python/module:'+data.__name__, '') + + def represent_object(self, data): + # We use __reduce__ API to save the data. data.__reduce__ returns + # a tuple of length 2-5: + # (function, args, state, listitems, dictitems) + + # For reconstructing, we calls function(*args), then set its state, + # listitems, and dictitems if they are not None. + + # A special case is when function.__name__ == '__newobj__'. In this + # case we create the object with args[0].__new__(*args). + + # Another special case is when __reduce__ returns a string - we don't + # support it. + + # We produce a !!python/object, !!python/object/new or + # !!python/object/apply node. + + cls = type(data) + if cls in copyreg.dispatch_table: + reduce = copyreg.dispatch_table[cls](data) + elif hasattr(data, '__reduce_ex__'): + reduce = data.__reduce_ex__(2) + elif hasattr(data, '__reduce__'): + reduce = data.__reduce__() + else: + raise RepresenterError("cannot represent an object", data) + reduce = (list(reduce)+[None]*5)[:5] + function, args, state, listitems, dictitems = reduce + args = list(args) + if state is None: + state = {} + if listitems is not None: + listitems = list(listitems) + if dictitems is not None: + dictitems = dict(dictitems) + if function.__name__ == '__newobj__': + function = args[0] + args = args[1:] + tag = 'tag:yaml.org,2002:python/object/new:' + newobj = True + else: + tag = 'tag:yaml.org,2002:python/object/apply:' + newobj = False + function_name = '%s.%s' % (function.__module__, function.__name__) + if not args and not listitems and not dictitems \ + and isinstance(state, dict) and newobj: + return self.represent_mapping( + 'tag:yaml.org,2002:python/object:'+function_name, state) + if not listitems and not dictitems \ + and isinstance(state, dict) and not state: + return self.represent_sequence(tag+function_name, args) + value = {} + if args: + value['args'] = args + if state or not isinstance(state, dict): + value['state'] = state + if listitems: + value['listitems'] = listitems + if dictitems: + value['dictitems'] = dictitems + return self.represent_mapping(tag+function_name, value) + + def represent_ordered_dict(self, data): + # Provide uniform representation across different Python versions. + data_type = type(data) + tag = 'tag:yaml.org,2002:python/object/apply:%s.%s' \ + % (data_type.__module__, data_type.__name__) + items = [[key, value] for key, value in data.items()] + return self.represent_sequence(tag, [items]) + +Representer.add_representer(complex, + Representer.represent_complex) + +Representer.add_representer(tuple, + Representer.represent_tuple) + +Representer.add_representer(type, + Representer.represent_name) + +Representer.add_representer(collections.OrderedDict, + Representer.represent_ordered_dict) + +Representer.add_representer(types.FunctionType, + Representer.represent_name) + +Representer.add_representer(types.BuiltinFunctionType, + Representer.represent_name) + +Representer.add_representer(types.ModuleType, + Representer.represent_module) + +Representer.add_multi_representer(object, + Representer.represent_object) + diff --git a/third_party/python/PyYAML/lib3/yaml/resolver.py b/third_party/python/PyYAML/lib3/yaml/resolver.py new file mode 100644 index 0000000000..013896d2f1 --- /dev/null +++ b/third_party/python/PyYAML/lib3/yaml/resolver.py @@ -0,0 +1,227 @@ + +__all__ = ['BaseResolver', 'Resolver'] + +from .error import * +from .nodes import * + +import re + +class ResolverError(YAMLError): + pass + +class BaseResolver: + + DEFAULT_SCALAR_TAG = 'tag:yaml.org,2002:str' + DEFAULT_SEQUENCE_TAG = 'tag:yaml.org,2002:seq' + DEFAULT_MAPPING_TAG = 'tag:yaml.org,2002:map' + + yaml_implicit_resolvers = {} + yaml_path_resolvers = {} + + def __init__(self): + self.resolver_exact_paths = [] + self.resolver_prefix_paths = [] + + @classmethod + def add_implicit_resolver(cls, tag, regexp, first): + if not 'yaml_implicit_resolvers' in cls.__dict__: + implicit_resolvers = {} + for key in cls.yaml_implicit_resolvers: + implicit_resolvers[key] = cls.yaml_implicit_resolvers[key][:] + cls.yaml_implicit_resolvers = implicit_resolvers + if first is None: + first = [None] + for ch in first: + cls.yaml_implicit_resolvers.setdefault(ch, []).append((tag, regexp)) + + @classmethod + def add_path_resolver(cls, tag, path, kind=None): + # Note: `add_path_resolver` is experimental. The API could be changed. + # `new_path` is a pattern that is matched against the path from the + # root to the node that is being considered. `node_path` elements are + # tuples `(node_check, index_check)`. `node_check` is a node class: + # `ScalarNode`, `SequenceNode`, `MappingNode` or `None`. `None` + # matches any kind of a node. `index_check` could be `None`, a boolean + # value, a string value, or a number. `None` and `False` match against + # any _value_ of sequence and mapping nodes. `True` matches against + # any _key_ of a mapping node. A string `index_check` matches against + # a mapping value that corresponds to a scalar key which content is + # equal to the `index_check` value. An integer `index_check` matches + # against a sequence value with the index equal to `index_check`. + if not 'yaml_path_resolvers' in cls.__dict__: + cls.yaml_path_resolvers = cls.yaml_path_resolvers.copy() + new_path = [] + for element in path: + if isinstance(element, (list, tuple)): + if len(element) == 2: + node_check, index_check = element + elif len(element) == 1: + node_check = element[0] + index_check = True + else: + raise ResolverError("Invalid path element: %s" % element) + else: + node_check = None + index_check = element + if node_check is str: + node_check = ScalarNode + elif node_check is list: + node_check = SequenceNode + elif node_check is dict: + node_check = MappingNode + elif node_check not in [ScalarNode, SequenceNode, MappingNode] \ + and not isinstance(node_check, str) \ + and node_check is not None: + raise ResolverError("Invalid node checker: %s" % node_check) + if not isinstance(index_check, (str, int)) \ + and index_check is not None: + raise ResolverError("Invalid index checker: %s" % index_check) + new_path.append((node_check, index_check)) + if kind is str: + kind = ScalarNode + elif kind is list: + kind = SequenceNode + elif kind is dict: + kind = MappingNode + elif kind not in [ScalarNode, SequenceNode, MappingNode] \ + and kind is not None: + raise ResolverError("Invalid node kind: %s" % kind) + cls.yaml_path_resolvers[tuple(new_path), kind] = tag + + def descend_resolver(self, current_node, current_index): + if not self.yaml_path_resolvers: + return + exact_paths = {} + prefix_paths = [] + if current_node: + depth = len(self.resolver_prefix_paths) + for path, kind in self.resolver_prefix_paths[-1]: + if self.check_resolver_prefix(depth, path, kind, + current_node, current_index): + if len(path) > depth: + prefix_paths.append((path, kind)) + else: + exact_paths[kind] = self.yaml_path_resolvers[path, kind] + else: + for path, kind in self.yaml_path_resolvers: + if not path: + exact_paths[kind] = self.yaml_path_resolvers[path, kind] + else: + prefix_paths.append((path, kind)) + self.resolver_exact_paths.append(exact_paths) + self.resolver_prefix_paths.append(prefix_paths) + + def ascend_resolver(self): + if not self.yaml_path_resolvers: + return + self.resolver_exact_paths.pop() + self.resolver_prefix_paths.pop() + + def check_resolver_prefix(self, depth, path, kind, + current_node, current_index): + node_check, index_check = path[depth-1] + if isinstance(node_check, str): + if current_node.tag != node_check: + return + elif node_check is not None: + if not isinstance(current_node, node_check): + return + if index_check is True and current_index is not None: + return + if (index_check is False or index_check is None) \ + and current_index is None: + return + if isinstance(index_check, str): + if not (isinstance(current_index, ScalarNode) + and index_check == current_index.value): + return + elif isinstance(index_check, int) and not isinstance(index_check, bool): + if index_check != current_index: + return + return True + + def resolve(self, kind, value, implicit): + if kind is ScalarNode and implicit[0]: + if value == '': + resolvers = self.yaml_implicit_resolvers.get('', []) + else: + resolvers = self.yaml_implicit_resolvers.get(value[0], []) + wildcard_resolvers = self.yaml_implicit_resolvers.get(None, []) + for tag, regexp in resolvers + wildcard_resolvers: + if regexp.match(value): + return tag + implicit = implicit[1] + if self.yaml_path_resolvers: + exact_paths = self.resolver_exact_paths[-1] + if kind in exact_paths: + return exact_paths[kind] + if None in exact_paths: + return exact_paths[None] + if kind is ScalarNode: + return self.DEFAULT_SCALAR_TAG + elif kind is SequenceNode: + return self.DEFAULT_SEQUENCE_TAG + elif kind is MappingNode: + return self.DEFAULT_MAPPING_TAG + +class Resolver(BaseResolver): + pass + +Resolver.add_implicit_resolver( + 'tag:yaml.org,2002:bool', + re.compile(r'''^(?:yes|Yes|YES|no|No|NO + |true|True|TRUE|false|False|FALSE + |on|On|ON|off|Off|OFF)$''', re.X), + list('yYnNtTfFoO')) + +Resolver.add_implicit_resolver( + 'tag:yaml.org,2002:float', + re.compile(r'''^(?:[-+]?(?:[0-9][0-9_]*)\.[0-9_]*(?:[eE][-+][0-9]+)? + |\.[0-9_]+(?:[eE][-+][0-9]+)? + |[-+]?[0-9][0-9_]*(?::[0-5]?[0-9])+\.[0-9_]* + |[-+]?\.(?:inf|Inf|INF) + |\.(?:nan|NaN|NAN))$''', re.X), + list('-+0123456789.')) + +Resolver.add_implicit_resolver( + 'tag:yaml.org,2002:int', + re.compile(r'''^(?:[-+]?0b[0-1_]+ + |[-+]?0[0-7_]+ + |[-+]?(?:0|[1-9][0-9_]*) + |[-+]?0x[0-9a-fA-F_]+ + |[-+]?[1-9][0-9_]*(?::[0-5]?[0-9])+)$''', re.X), + list('-+0123456789')) + +Resolver.add_implicit_resolver( + 'tag:yaml.org,2002:merge', + re.compile(r'^(?:<<)$'), + ['<']) + +Resolver.add_implicit_resolver( + 'tag:yaml.org,2002:null', + re.compile(r'''^(?: ~ + |null|Null|NULL + | )$''', re.X), + ['~', 'n', 'N', '']) + +Resolver.add_implicit_resolver( + 'tag:yaml.org,2002:timestamp', + re.compile(r'''^(?:[0-9][0-9][0-9][0-9]-[0-9][0-9]-[0-9][0-9] + |[0-9][0-9][0-9][0-9] -[0-9][0-9]? -[0-9][0-9]? + (?:[Tt]|[ \t]+)[0-9][0-9]? + :[0-9][0-9] :[0-9][0-9] (?:\.[0-9]*)? + (?:[ \t]*(?:Z|[-+][0-9][0-9]?(?::[0-9][0-9])?))?)$''', re.X), + list('0123456789')) + +Resolver.add_implicit_resolver( + 'tag:yaml.org,2002:value', + re.compile(r'^(?:=)$'), + ['=']) + +# The following resolver is only for documentation purposes. It cannot work +# because plain scalars cannot start with '!', '&', or '*'. +Resolver.add_implicit_resolver( + 'tag:yaml.org,2002:yaml', + re.compile(r'^(?:!|&|\*)$'), + list('!&*')) + diff --git a/third_party/python/PyYAML/lib3/yaml/scanner.py b/third_party/python/PyYAML/lib3/yaml/scanner.py new file mode 100644 index 0000000000..7437ede1c6 --- /dev/null +++ b/third_party/python/PyYAML/lib3/yaml/scanner.py @@ -0,0 +1,1435 @@ + +# Scanner produces tokens of the following types: +# STREAM-START +# STREAM-END +# DIRECTIVE(name, value) +# DOCUMENT-START +# DOCUMENT-END +# BLOCK-SEQUENCE-START +# BLOCK-MAPPING-START +# BLOCK-END +# FLOW-SEQUENCE-START +# FLOW-MAPPING-START +# FLOW-SEQUENCE-END +# FLOW-MAPPING-END +# BLOCK-ENTRY +# FLOW-ENTRY +# KEY +# VALUE +# ALIAS(value) +# ANCHOR(value) +# TAG(value) +# SCALAR(value, plain, style) +# +# Read comments in the Scanner code for more details. +# + +__all__ = ['Scanner', 'ScannerError'] + +from .error import MarkedYAMLError +from .tokens import * + +class ScannerError(MarkedYAMLError): + pass + +class SimpleKey: + # See below simple keys treatment. + + def __init__(self, token_number, required, index, line, column, mark): + self.token_number = token_number + self.required = required + self.index = index + self.line = line + self.column = column + self.mark = mark + +class Scanner: + + def __init__(self): + """Initialize the scanner.""" + # It is assumed that Scanner and Reader will have a common descendant. + # Reader do the dirty work of checking for BOM and converting the + # input data to Unicode. It also adds NUL to the end. + # + # Reader supports the following methods + # self.peek(i=0) # peek the next i-th character + # self.prefix(l=1) # peek the next l characters + # self.forward(l=1) # read the next l characters and move the pointer. + + # Had we reached the end of the stream? + self.done = False + + # The number of unclosed '{' and '['. `flow_level == 0` means block + # context. + self.flow_level = 0 + + # List of processed tokens that are not yet emitted. + self.tokens = [] + + # Add the STREAM-START token. + self.fetch_stream_start() + + # Number of tokens that were emitted through the `get_token` method. + self.tokens_taken = 0 + + # The current indentation level. + self.indent = -1 + + # Past indentation levels. + self.indents = [] + + # Variables related to simple keys treatment. + + # A simple key is a key that is not denoted by the '?' indicator. + # Example of simple keys: + # --- + # block simple key: value + # ? not a simple key: + # : { flow simple key: value } + # We emit the KEY token before all keys, so when we find a potential + # simple key, we try to locate the corresponding ':' indicator. + # Simple keys should be limited to a single line and 1024 characters. + + # Can a simple key start at the current position? A simple key may + # start: + # - at the beginning of the line, not counting indentation spaces + # (in block context), + # - after '{', '[', ',' (in the flow context), + # - after '?', ':', '-' (in the block context). + # In the block context, this flag also signifies if a block collection + # may start at the current position. + self.allow_simple_key = True + + # Keep track of possible simple keys. This is a dictionary. The key + # is `flow_level`; there can be no more that one possible simple key + # for each level. The value is a SimpleKey record: + # (token_number, required, index, line, column, mark) + # A simple key may start with ALIAS, ANCHOR, TAG, SCALAR(flow), + # '[', or '{' tokens. + self.possible_simple_keys = {} + + # Public methods. + + def check_token(self, *choices): + # Check if the next token is one of the given types. + while self.need_more_tokens(): + self.fetch_more_tokens() + if self.tokens: + if not choices: + return True + for choice in choices: + if isinstance(self.tokens[0], choice): + return True + return False + + def peek_token(self): + # Return the next token, but do not delete if from the queue. + # Return None if no more tokens. + while self.need_more_tokens(): + self.fetch_more_tokens() + if self.tokens: + return self.tokens[0] + else: + return None + + def get_token(self): + # Return the next token. + while self.need_more_tokens(): + self.fetch_more_tokens() + if self.tokens: + self.tokens_taken += 1 + return self.tokens.pop(0) + + # Private methods. + + def need_more_tokens(self): + if self.done: + return False + if not self.tokens: + return True + # The current token may be a potential simple key, so we + # need to look further. + self.stale_possible_simple_keys() + if self.next_possible_simple_key() == self.tokens_taken: + return True + + def fetch_more_tokens(self): + + # Eat whitespaces and comments until we reach the next token. + self.scan_to_next_token() + + # Remove obsolete possible simple keys. + self.stale_possible_simple_keys() + + # Compare the current indentation and column. It may add some tokens + # and decrease the current indentation level. + self.unwind_indent(self.column) + + # Peek the next character. + ch = self.peek() + + # Is it the end of stream? + if ch == '\0': + return self.fetch_stream_end() + + # Is it a directive? + if ch == '%' and self.check_directive(): + return self.fetch_directive() + + # Is it the document start? + if ch == '-' and self.check_document_start(): + return self.fetch_document_start() + + # Is it the document end? + if ch == '.' and self.check_document_end(): + return self.fetch_document_end() + + # TODO: support for BOM within a stream. + #if ch == '\uFEFF': + # return self.fetch_bom() <-- issue BOMToken + + # Note: the order of the following checks is NOT significant. + + # Is it the flow sequence start indicator? + if ch == '[': + return self.fetch_flow_sequence_start() + + # Is it the flow mapping start indicator? + if ch == '{': + return self.fetch_flow_mapping_start() + + # Is it the flow sequence end indicator? + if ch == ']': + return self.fetch_flow_sequence_end() + + # Is it the flow mapping end indicator? + if ch == '}': + return self.fetch_flow_mapping_end() + + # Is it the flow entry indicator? + if ch == ',': + return self.fetch_flow_entry() + + # Is it the block entry indicator? + if ch == '-' and self.check_block_entry(): + return self.fetch_block_entry() + + # Is it the key indicator? + if ch == '?' and self.check_key(): + return self.fetch_key() + + # Is it the value indicator? + if ch == ':' and self.check_value(): + return self.fetch_value() + + # Is it an alias? + if ch == '*': + return self.fetch_alias() + + # Is it an anchor? + if ch == '&': + return self.fetch_anchor() + + # Is it a tag? + if ch == '!': + return self.fetch_tag() + + # Is it a literal scalar? + if ch == '|' and not self.flow_level: + return self.fetch_literal() + + # Is it a folded scalar? + if ch == '>' and not self.flow_level: + return self.fetch_folded() + + # Is it a single quoted scalar? + if ch == '\'': + return self.fetch_single() + + # Is it a double quoted scalar? + if ch == '\"': + return self.fetch_double() + + # It must be a plain scalar then. + if self.check_plain(): + return self.fetch_plain() + + # No? It's an error. Let's produce a nice error message. + raise ScannerError("while scanning for the next token", None, + "found character %r that cannot start any token" % ch, + self.get_mark()) + + # Simple keys treatment. + + def next_possible_simple_key(self): + # Return the number of the nearest possible simple key. Actually we + # don't need to loop through the whole dictionary. We may replace it + # with the following code: + # if not self.possible_simple_keys: + # return None + # return self.possible_simple_keys[ + # min(self.possible_simple_keys.keys())].token_number + min_token_number = None + for level in self.possible_simple_keys: + key = self.possible_simple_keys[level] + if min_token_number is None or key.token_number < min_token_number: + min_token_number = key.token_number + return min_token_number + + def stale_possible_simple_keys(self): + # Remove entries that are no longer possible simple keys. According to + # the YAML specification, simple keys + # - should be limited to a single line, + # - should be no longer than 1024 characters. + # Disabling this procedure will allow simple keys of any length and + # height (may cause problems if indentation is broken though). + for level in list(self.possible_simple_keys): + key = self.possible_simple_keys[level] + if key.line != self.line \ + or self.index-key.index > 1024: + if key.required: + raise ScannerError("while scanning a simple key", key.mark, + "could not find expected ':'", self.get_mark()) + del self.possible_simple_keys[level] + + def save_possible_simple_key(self): + # The next token may start a simple key. We check if it's possible + # and save its position. This function is called for + # ALIAS, ANCHOR, TAG, SCALAR(flow), '[', and '{'. + + # Check if a simple key is required at the current position. + required = not self.flow_level and self.indent == self.column + + # The next token might be a simple key. Let's save it's number and + # position. + if self.allow_simple_key: + self.remove_possible_simple_key() + token_number = self.tokens_taken+len(self.tokens) + key = SimpleKey(token_number, required, + self.index, self.line, self.column, self.get_mark()) + self.possible_simple_keys[self.flow_level] = key + + def remove_possible_simple_key(self): + # Remove the saved possible key position at the current flow level. + if self.flow_level in self.possible_simple_keys: + key = self.possible_simple_keys[self.flow_level] + + if key.required: + raise ScannerError("while scanning a simple key", key.mark, + "could not find expected ':'", self.get_mark()) + + del self.possible_simple_keys[self.flow_level] + + # Indentation functions. + + def unwind_indent(self, column): + + ## In flow context, tokens should respect indentation. + ## Actually the condition should be `self.indent >= column` according to + ## the spec. But this condition will prohibit intuitively correct + ## constructions such as + ## key : { + ## } + #if self.flow_level and self.indent > column: + # raise ScannerError(None, None, + # "invalid indentation or unclosed '[' or '{'", + # self.get_mark()) + + # In the flow context, indentation is ignored. We make the scanner less + # restrictive then specification requires. + if self.flow_level: + return + + # In block context, we may need to issue the BLOCK-END tokens. + while self.indent > column: + mark = self.get_mark() + self.indent = self.indents.pop() + self.tokens.append(BlockEndToken(mark, mark)) + + def add_indent(self, column): + # Check if we need to increase indentation. + if self.indent < column: + self.indents.append(self.indent) + self.indent = column + return True + return False + + # Fetchers. + + def fetch_stream_start(self): + # We always add STREAM-START as the first token and STREAM-END as the + # last token. + + # Read the token. + mark = self.get_mark() + + # Add STREAM-START. + self.tokens.append(StreamStartToken(mark, mark, + encoding=self.encoding)) + + + def fetch_stream_end(self): + + # Set the current indentation to -1. + self.unwind_indent(-1) + + # Reset simple keys. + self.remove_possible_simple_key() + self.allow_simple_key = False + self.possible_simple_keys = {} + + # Read the token. + mark = self.get_mark() + + # Add STREAM-END. + self.tokens.append(StreamEndToken(mark, mark)) + + # The steam is finished. + self.done = True + + def fetch_directive(self): + + # Set the current indentation to -1. + self.unwind_indent(-1) + + # Reset simple keys. + self.remove_possible_simple_key() + self.allow_simple_key = False + + # Scan and add DIRECTIVE. + self.tokens.append(self.scan_directive()) + + def fetch_document_start(self): + self.fetch_document_indicator(DocumentStartToken) + + def fetch_document_end(self): + self.fetch_document_indicator(DocumentEndToken) + + def fetch_document_indicator(self, TokenClass): + + # Set the current indentation to -1. + self.unwind_indent(-1) + + # Reset simple keys. Note that there could not be a block collection + # after '---'. + self.remove_possible_simple_key() + self.allow_simple_key = False + + # Add DOCUMENT-START or DOCUMENT-END. + start_mark = self.get_mark() + self.forward(3) + end_mark = self.get_mark() + self.tokens.append(TokenClass(start_mark, end_mark)) + + def fetch_flow_sequence_start(self): + self.fetch_flow_collection_start(FlowSequenceStartToken) + + def fetch_flow_mapping_start(self): + self.fetch_flow_collection_start(FlowMappingStartToken) + + def fetch_flow_collection_start(self, TokenClass): + + # '[' and '{' may start a simple key. + self.save_possible_simple_key() + + # Increase the flow level. + self.flow_level += 1 + + # Simple keys are allowed after '[' and '{'. + self.allow_simple_key = True + + # Add FLOW-SEQUENCE-START or FLOW-MAPPING-START. + start_mark = self.get_mark() + self.forward() + end_mark = self.get_mark() + self.tokens.append(TokenClass(start_mark, end_mark)) + + def fetch_flow_sequence_end(self): + self.fetch_flow_collection_end(FlowSequenceEndToken) + + def fetch_flow_mapping_end(self): + self.fetch_flow_collection_end(FlowMappingEndToken) + + def fetch_flow_collection_end(self, TokenClass): + + # Reset possible simple key on the current level. + self.remove_possible_simple_key() + + # Decrease the flow level. + self.flow_level -= 1 + + # No simple keys after ']' or '}'. + self.allow_simple_key = False + + # Add FLOW-SEQUENCE-END or FLOW-MAPPING-END. + start_mark = self.get_mark() + self.forward() + end_mark = self.get_mark() + self.tokens.append(TokenClass(start_mark, end_mark)) + + def fetch_flow_entry(self): + + # Simple keys are allowed after ','. + self.allow_simple_key = True + + # Reset possible simple key on the current level. + self.remove_possible_simple_key() + + # Add FLOW-ENTRY. + start_mark = self.get_mark() + self.forward() + end_mark = self.get_mark() + self.tokens.append(FlowEntryToken(start_mark, end_mark)) + + def fetch_block_entry(self): + + # Block context needs additional checks. + if not self.flow_level: + + # Are we allowed to start a new entry? + if not self.allow_simple_key: + raise ScannerError(None, None, + "sequence entries are not allowed here", + self.get_mark()) + + # We may need to add BLOCK-SEQUENCE-START. + if self.add_indent(self.column): + mark = self.get_mark() + self.tokens.append(BlockSequenceStartToken(mark, mark)) + + # It's an error for the block entry to occur in the flow context, + # but we let the parser detect this. + else: + pass + + # Simple keys are allowed after '-'. + self.allow_simple_key = True + + # Reset possible simple key on the current level. + self.remove_possible_simple_key() + + # Add BLOCK-ENTRY. + start_mark = self.get_mark() + self.forward() + end_mark = self.get_mark() + self.tokens.append(BlockEntryToken(start_mark, end_mark)) + + def fetch_key(self): + + # Block context needs additional checks. + if not self.flow_level: + + # Are we allowed to start a key (not necessary a simple)? + if not self.allow_simple_key: + raise ScannerError(None, None, + "mapping keys are not allowed here", + self.get_mark()) + + # We may need to add BLOCK-MAPPING-START. + if self.add_indent(self.column): + mark = self.get_mark() + self.tokens.append(BlockMappingStartToken(mark, mark)) + + # Simple keys are allowed after '?' in the block context. + self.allow_simple_key = not self.flow_level + + # Reset possible simple key on the current level. + self.remove_possible_simple_key() + + # Add KEY. + start_mark = self.get_mark() + self.forward() + end_mark = self.get_mark() + self.tokens.append(KeyToken(start_mark, end_mark)) + + def fetch_value(self): + + # Do we determine a simple key? + if self.flow_level in self.possible_simple_keys: + + # Add KEY. + key = self.possible_simple_keys[self.flow_level] + del self.possible_simple_keys[self.flow_level] + self.tokens.insert(key.token_number-self.tokens_taken, + KeyToken(key.mark, key.mark)) + + # If this key starts a new block mapping, we need to add + # BLOCK-MAPPING-START. + if not self.flow_level: + if self.add_indent(key.column): + self.tokens.insert(key.token_number-self.tokens_taken, + BlockMappingStartToken(key.mark, key.mark)) + + # There cannot be two simple keys one after another. + self.allow_simple_key = False + + # It must be a part of a complex key. + else: + + # Block context needs additional checks. + # (Do we really need them? They will be caught by the parser + # anyway.) + if not self.flow_level: + + # We are allowed to start a complex value if and only if + # we can start a simple key. + if not self.allow_simple_key: + raise ScannerError(None, None, + "mapping values are not allowed here", + self.get_mark()) + + # If this value starts a new block mapping, we need to add + # BLOCK-MAPPING-START. It will be detected as an error later by + # the parser. + if not self.flow_level: + if self.add_indent(self.column): + mark = self.get_mark() + self.tokens.append(BlockMappingStartToken(mark, mark)) + + # Simple keys are allowed after ':' in the block context. + self.allow_simple_key = not self.flow_level + + # Reset possible simple key on the current level. + self.remove_possible_simple_key() + + # Add VALUE. + start_mark = self.get_mark() + self.forward() + end_mark = self.get_mark() + self.tokens.append(ValueToken(start_mark, end_mark)) + + def fetch_alias(self): + + # ALIAS could be a simple key. + self.save_possible_simple_key() + + # No simple keys after ALIAS. + self.allow_simple_key = False + + # Scan and add ALIAS. + self.tokens.append(self.scan_anchor(AliasToken)) + + def fetch_anchor(self): + + # ANCHOR could start a simple key. + self.save_possible_simple_key() + + # No simple keys after ANCHOR. + self.allow_simple_key = False + + # Scan and add ANCHOR. + self.tokens.append(self.scan_anchor(AnchorToken)) + + def fetch_tag(self): + + # TAG could start a simple key. + self.save_possible_simple_key() + + # No simple keys after TAG. + self.allow_simple_key = False + + # Scan and add TAG. + self.tokens.append(self.scan_tag()) + + def fetch_literal(self): + self.fetch_block_scalar(style='|') + + def fetch_folded(self): + self.fetch_block_scalar(style='>') + + def fetch_block_scalar(self, style): + + # A simple key may follow a block scalar. + self.allow_simple_key = True + + # Reset possible simple key on the current level. + self.remove_possible_simple_key() + + # Scan and add SCALAR. + self.tokens.append(self.scan_block_scalar(style)) + + def fetch_single(self): + self.fetch_flow_scalar(style='\'') + + def fetch_double(self): + self.fetch_flow_scalar(style='"') + + def fetch_flow_scalar(self, style): + + # A flow scalar could be a simple key. + self.save_possible_simple_key() + + # No simple keys after flow scalars. + self.allow_simple_key = False + + # Scan and add SCALAR. + self.tokens.append(self.scan_flow_scalar(style)) + + def fetch_plain(self): + + # A plain scalar could be a simple key. + self.save_possible_simple_key() + + # No simple keys after plain scalars. But note that `scan_plain` will + # change this flag if the scan is finished at the beginning of the + # line. + self.allow_simple_key = False + + # Scan and add SCALAR. May change `allow_simple_key`. + self.tokens.append(self.scan_plain()) + + # Checkers. + + def check_directive(self): + + # DIRECTIVE: ^ '%' ... + # The '%' indicator is already checked. + if self.column == 0: + return True + + def check_document_start(self): + + # DOCUMENT-START: ^ '---' (' '|'\n') + if self.column == 0: + if self.prefix(3) == '---' \ + and self.peek(3) in '\0 \t\r\n\x85\u2028\u2029': + return True + + def check_document_end(self): + + # DOCUMENT-END: ^ '...' (' '|'\n') + if self.column == 0: + if self.prefix(3) == '...' \ + and self.peek(3) in '\0 \t\r\n\x85\u2028\u2029': + return True + + def check_block_entry(self): + + # BLOCK-ENTRY: '-' (' '|'\n') + return self.peek(1) in '\0 \t\r\n\x85\u2028\u2029' + + def check_key(self): + + # KEY(flow context): '?' + if self.flow_level: + return True + + # KEY(block context): '?' (' '|'\n') + else: + return self.peek(1) in '\0 \t\r\n\x85\u2028\u2029' + + def check_value(self): + + # VALUE(flow context): ':' + if self.flow_level: + return True + + # VALUE(block context): ':' (' '|'\n') + else: + return self.peek(1) in '\0 \t\r\n\x85\u2028\u2029' + + def check_plain(self): + + # A plain scalar may start with any non-space character except: + # '-', '?', ':', ',', '[', ']', '{', '}', + # '#', '&', '*', '!', '|', '>', '\'', '\"', + # '%', '@', '`'. + # + # It may also start with + # '-', '?', ':' + # if it is followed by a non-space character. + # + # Note that we limit the last rule to the block context (except the + # '-' character) because we want the flow context to be space + # independent. + ch = self.peek() + return ch not in '\0 \t\r\n\x85\u2028\u2029-?:,[]{}#&*!|>\'\"%@`' \ + or (self.peek(1) not in '\0 \t\r\n\x85\u2028\u2029' + and (ch == '-' or (not self.flow_level and ch in '?:'))) + + # Scanners. + + def scan_to_next_token(self): + # We ignore spaces, line breaks and comments. + # If we find a line break in the block context, we set the flag + # `allow_simple_key` on. + # The byte order mark is stripped if it's the first character in the + # stream. We do not yet support BOM inside the stream as the + # specification requires. Any such mark will be considered as a part + # of the document. + # + # TODO: We need to make tab handling rules more sane. A good rule is + # Tabs cannot precede tokens + # BLOCK-SEQUENCE-START, BLOCK-MAPPING-START, BLOCK-END, + # KEY(block), VALUE(block), BLOCK-ENTRY + # So the checking code is + # if : + # self.allow_simple_keys = False + # We also need to add the check for `allow_simple_keys == True` to + # `unwind_indent` before issuing BLOCK-END. + # Scanners for block, flow, and plain scalars need to be modified. + + if self.index == 0 and self.peek() == '\uFEFF': + self.forward() + found = False + while not found: + while self.peek() == ' ': + self.forward() + if self.peek() == '#': + while self.peek() not in '\0\r\n\x85\u2028\u2029': + self.forward() + if self.scan_line_break(): + if not self.flow_level: + self.allow_simple_key = True + else: + found = True + + def scan_directive(self): + # See the specification for details. + start_mark = self.get_mark() + self.forward() + name = self.scan_directive_name(start_mark) + value = None + if name == 'YAML': + value = self.scan_yaml_directive_value(start_mark) + end_mark = self.get_mark() + elif name == 'TAG': + value = self.scan_tag_directive_value(start_mark) + end_mark = self.get_mark() + else: + end_mark = self.get_mark() + while self.peek() not in '\0\r\n\x85\u2028\u2029': + self.forward() + self.scan_directive_ignored_line(start_mark) + return DirectiveToken(name, value, start_mark, end_mark) + + def scan_directive_name(self, start_mark): + # See the specification for details. + length = 0 + ch = self.peek(length) + while '0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ + or ch in '-_': + length += 1 + ch = self.peek(length) + if not length: + raise ScannerError("while scanning a directive", start_mark, + "expected alphabetic or numeric character, but found %r" + % ch, self.get_mark()) + value = self.prefix(length) + self.forward(length) + ch = self.peek() + if ch not in '\0 \r\n\x85\u2028\u2029': + raise ScannerError("while scanning a directive", start_mark, + "expected alphabetic or numeric character, but found %r" + % ch, self.get_mark()) + return value + + def scan_yaml_directive_value(self, start_mark): + # See the specification for details. + while self.peek() == ' ': + self.forward() + major = self.scan_yaml_directive_number(start_mark) + if self.peek() != '.': + raise ScannerError("while scanning a directive", start_mark, + "expected a digit or '.', but found %r" % self.peek(), + self.get_mark()) + self.forward() + minor = self.scan_yaml_directive_number(start_mark) + if self.peek() not in '\0 \r\n\x85\u2028\u2029': + raise ScannerError("while scanning a directive", start_mark, + "expected a digit or ' ', but found %r" % self.peek(), + self.get_mark()) + return (major, minor) + + def scan_yaml_directive_number(self, start_mark): + # See the specification for details. + ch = self.peek() + if not ('0' <= ch <= '9'): + raise ScannerError("while scanning a directive", start_mark, + "expected a digit, but found %r" % ch, self.get_mark()) + length = 0 + while '0' <= self.peek(length) <= '9': + length += 1 + value = int(self.prefix(length)) + self.forward(length) + return value + + def scan_tag_directive_value(self, start_mark): + # See the specification for details. + while self.peek() == ' ': + self.forward() + handle = self.scan_tag_directive_handle(start_mark) + while self.peek() == ' ': + self.forward() + prefix = self.scan_tag_directive_prefix(start_mark) + return (handle, prefix) + + def scan_tag_directive_handle(self, start_mark): + # See the specification for details. + value = self.scan_tag_handle('directive', start_mark) + ch = self.peek() + if ch != ' ': + raise ScannerError("while scanning a directive", start_mark, + "expected ' ', but found %r" % ch, self.get_mark()) + return value + + def scan_tag_directive_prefix(self, start_mark): + # See the specification for details. + value = self.scan_tag_uri('directive', start_mark) + ch = self.peek() + if ch not in '\0 \r\n\x85\u2028\u2029': + raise ScannerError("while scanning a directive", start_mark, + "expected ' ', but found %r" % ch, self.get_mark()) + return value + + def scan_directive_ignored_line(self, start_mark): + # See the specification for details. + while self.peek() == ' ': + self.forward() + if self.peek() == '#': + while self.peek() not in '\0\r\n\x85\u2028\u2029': + self.forward() + ch = self.peek() + if ch not in '\0\r\n\x85\u2028\u2029': + raise ScannerError("while scanning a directive", start_mark, + "expected a comment or a line break, but found %r" + % ch, self.get_mark()) + self.scan_line_break() + + def scan_anchor(self, TokenClass): + # The specification does not restrict characters for anchors and + # aliases. This may lead to problems, for instance, the document: + # [ *alias, value ] + # can be interpreted in two ways, as + # [ "value" ] + # and + # [ *alias , "value" ] + # Therefore we restrict aliases to numbers and ASCII letters. + start_mark = self.get_mark() + indicator = self.peek() + if indicator == '*': + name = 'alias' + else: + name = 'anchor' + self.forward() + length = 0 + ch = self.peek(length) + while '0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ + or ch in '-_': + length += 1 + ch = self.peek(length) + if not length: + raise ScannerError("while scanning an %s" % name, start_mark, + "expected alphabetic or numeric character, but found %r" + % ch, self.get_mark()) + value = self.prefix(length) + self.forward(length) + ch = self.peek() + if ch not in '\0 \t\r\n\x85\u2028\u2029?:,]}%@`': + raise ScannerError("while scanning an %s" % name, start_mark, + "expected alphabetic or numeric character, but found %r" + % ch, self.get_mark()) + end_mark = self.get_mark() + return TokenClass(value, start_mark, end_mark) + + def scan_tag(self): + # See the specification for details. + start_mark = self.get_mark() + ch = self.peek(1) + if ch == '<': + handle = None + self.forward(2) + suffix = self.scan_tag_uri('tag', start_mark) + if self.peek() != '>': + raise ScannerError("while parsing a tag", start_mark, + "expected '>', but found %r" % self.peek(), + self.get_mark()) + self.forward() + elif ch in '\0 \t\r\n\x85\u2028\u2029': + handle = None + suffix = '!' + self.forward() + else: + length = 1 + use_handle = False + while ch not in '\0 \r\n\x85\u2028\u2029': + if ch == '!': + use_handle = True + break + length += 1 + ch = self.peek(length) + handle = '!' + if use_handle: + handle = self.scan_tag_handle('tag', start_mark) + else: + handle = '!' + self.forward() + suffix = self.scan_tag_uri('tag', start_mark) + ch = self.peek() + if ch not in '\0 \r\n\x85\u2028\u2029': + raise ScannerError("while scanning a tag", start_mark, + "expected ' ', but found %r" % ch, self.get_mark()) + value = (handle, suffix) + end_mark = self.get_mark() + return TagToken(value, start_mark, end_mark) + + def scan_block_scalar(self, style): + # See the specification for details. + + if style == '>': + folded = True + else: + folded = False + + chunks = [] + start_mark = self.get_mark() + + # Scan the header. + self.forward() + chomping, increment = self.scan_block_scalar_indicators(start_mark) + self.scan_block_scalar_ignored_line(start_mark) + + # Determine the indentation level and go to the first non-empty line. + min_indent = self.indent+1 + if min_indent < 1: + min_indent = 1 + if increment is None: + breaks, max_indent, end_mark = self.scan_block_scalar_indentation() + indent = max(min_indent, max_indent) + else: + indent = min_indent+increment-1 + breaks, end_mark = self.scan_block_scalar_breaks(indent) + line_break = '' + + # Scan the inner part of the block scalar. + while self.column == indent and self.peek() != '\0': + chunks.extend(breaks) + leading_non_space = self.peek() not in ' \t' + length = 0 + while self.peek(length) not in '\0\r\n\x85\u2028\u2029': + length += 1 + chunks.append(self.prefix(length)) + self.forward(length) + line_break = self.scan_line_break() + breaks, end_mark = self.scan_block_scalar_breaks(indent) + if self.column == indent and self.peek() != '\0': + + # Unfortunately, folding rules are ambiguous. + # + # This is the folding according to the specification: + + if folded and line_break == '\n' \ + and leading_non_space and self.peek() not in ' \t': + if not breaks: + chunks.append(' ') + else: + chunks.append(line_break) + + # This is Clark Evans's interpretation (also in the spec + # examples): + # + #if folded and line_break == '\n': + # if not breaks: + # if self.peek() not in ' \t': + # chunks.append(' ') + # else: + # chunks.append(line_break) + #else: + # chunks.append(line_break) + else: + break + + # Chomp the tail. + if chomping is not False: + chunks.append(line_break) + if chomping is True: + chunks.extend(breaks) + + # We are done. + return ScalarToken(''.join(chunks), False, start_mark, end_mark, + style) + + def scan_block_scalar_indicators(self, start_mark): + # See the specification for details. + chomping = None + increment = None + ch = self.peek() + if ch in '+-': + if ch == '+': + chomping = True + else: + chomping = False + self.forward() + ch = self.peek() + if ch in '0123456789': + increment = int(ch) + if increment == 0: + raise ScannerError("while scanning a block scalar", start_mark, + "expected indentation indicator in the range 1-9, but found 0", + self.get_mark()) + self.forward() + elif ch in '0123456789': + increment = int(ch) + if increment == 0: + raise ScannerError("while scanning a block scalar", start_mark, + "expected indentation indicator in the range 1-9, but found 0", + self.get_mark()) + self.forward() + ch = self.peek() + if ch in '+-': + if ch == '+': + chomping = True + else: + chomping = False + self.forward() + ch = self.peek() + if ch not in '\0 \r\n\x85\u2028\u2029': + raise ScannerError("while scanning a block scalar", start_mark, + "expected chomping or indentation indicators, but found %r" + % ch, self.get_mark()) + return chomping, increment + + def scan_block_scalar_ignored_line(self, start_mark): + # See the specification for details. + while self.peek() == ' ': + self.forward() + if self.peek() == '#': + while self.peek() not in '\0\r\n\x85\u2028\u2029': + self.forward() + ch = self.peek() + if ch not in '\0\r\n\x85\u2028\u2029': + raise ScannerError("while scanning a block scalar", start_mark, + "expected a comment or a line break, but found %r" % ch, + self.get_mark()) + self.scan_line_break() + + def scan_block_scalar_indentation(self): + # See the specification for details. + chunks = [] + max_indent = 0 + end_mark = self.get_mark() + while self.peek() in ' \r\n\x85\u2028\u2029': + if self.peek() != ' ': + chunks.append(self.scan_line_break()) + end_mark = self.get_mark() + else: + self.forward() + if self.column > max_indent: + max_indent = self.column + return chunks, max_indent, end_mark + + def scan_block_scalar_breaks(self, indent): + # See the specification for details. + chunks = [] + end_mark = self.get_mark() + while self.column < indent and self.peek() == ' ': + self.forward() + while self.peek() in '\r\n\x85\u2028\u2029': + chunks.append(self.scan_line_break()) + end_mark = self.get_mark() + while self.column < indent and self.peek() == ' ': + self.forward() + return chunks, end_mark + + def scan_flow_scalar(self, style): + # See the specification for details. + # Note that we loose indentation rules for quoted scalars. Quoted + # scalars don't need to adhere indentation because " and ' clearly + # mark the beginning and the end of them. Therefore we are less + # restrictive then the specification requires. We only need to check + # that document separators are not included in scalars. + if style == '"': + double = True + else: + double = False + chunks = [] + start_mark = self.get_mark() + quote = self.peek() + self.forward() + chunks.extend(self.scan_flow_scalar_non_spaces(double, start_mark)) + while self.peek() != quote: + chunks.extend(self.scan_flow_scalar_spaces(double, start_mark)) + chunks.extend(self.scan_flow_scalar_non_spaces(double, start_mark)) + self.forward() + end_mark = self.get_mark() + return ScalarToken(''.join(chunks), False, start_mark, end_mark, + style) + + ESCAPE_REPLACEMENTS = { + '0': '\0', + 'a': '\x07', + 'b': '\x08', + 't': '\x09', + '\t': '\x09', + 'n': '\x0A', + 'v': '\x0B', + 'f': '\x0C', + 'r': '\x0D', + 'e': '\x1B', + ' ': '\x20', + '\"': '\"', + '\\': '\\', + '/': '/', + 'N': '\x85', + '_': '\xA0', + 'L': '\u2028', + 'P': '\u2029', + } + + ESCAPE_CODES = { + 'x': 2, + 'u': 4, + 'U': 8, + } + + def scan_flow_scalar_non_spaces(self, double, start_mark): + # See the specification for details. + chunks = [] + while True: + length = 0 + while self.peek(length) not in '\'\"\\\0 \t\r\n\x85\u2028\u2029': + length += 1 + if length: + chunks.append(self.prefix(length)) + self.forward(length) + ch = self.peek() + if not double and ch == '\'' and self.peek(1) == '\'': + chunks.append('\'') + self.forward(2) + elif (double and ch == '\'') or (not double and ch in '\"\\'): + chunks.append(ch) + self.forward() + elif double and ch == '\\': + self.forward() + ch = self.peek() + if ch in self.ESCAPE_REPLACEMENTS: + chunks.append(self.ESCAPE_REPLACEMENTS[ch]) + self.forward() + elif ch in self.ESCAPE_CODES: + length = self.ESCAPE_CODES[ch] + self.forward() + for k in range(length): + if self.peek(k) not in '0123456789ABCDEFabcdef': + raise ScannerError("while scanning a double-quoted scalar", start_mark, + "expected escape sequence of %d hexdecimal numbers, but found %r" % + (length, self.peek(k)), self.get_mark()) + code = int(self.prefix(length), 16) + chunks.append(chr(code)) + self.forward(length) + elif ch in '\r\n\x85\u2028\u2029': + self.scan_line_break() + chunks.extend(self.scan_flow_scalar_breaks(double, start_mark)) + else: + raise ScannerError("while scanning a double-quoted scalar", start_mark, + "found unknown escape character %r" % ch, self.get_mark()) + else: + return chunks + + def scan_flow_scalar_spaces(self, double, start_mark): + # See the specification for details. + chunks = [] + length = 0 + while self.peek(length) in ' \t': + length += 1 + whitespaces = self.prefix(length) + self.forward(length) + ch = self.peek() + if ch == '\0': + raise ScannerError("while scanning a quoted scalar", start_mark, + "found unexpected end of stream", self.get_mark()) + elif ch in '\r\n\x85\u2028\u2029': + line_break = self.scan_line_break() + breaks = self.scan_flow_scalar_breaks(double, start_mark) + if line_break != '\n': + chunks.append(line_break) + elif not breaks: + chunks.append(' ') + chunks.extend(breaks) + else: + chunks.append(whitespaces) + return chunks + + def scan_flow_scalar_breaks(self, double, start_mark): + # See the specification for details. + chunks = [] + while True: + # Instead of checking indentation, we check for document + # separators. + prefix = self.prefix(3) + if (prefix == '---' or prefix == '...') \ + and self.peek(3) in '\0 \t\r\n\x85\u2028\u2029': + raise ScannerError("while scanning a quoted scalar", start_mark, + "found unexpected document separator", self.get_mark()) + while self.peek() in ' \t': + self.forward() + if self.peek() in '\r\n\x85\u2028\u2029': + chunks.append(self.scan_line_break()) + else: + return chunks + + def scan_plain(self): + # See the specification for details. + # We add an additional restriction for the flow context: + # plain scalars in the flow context cannot contain ',' or '?'. + # We also keep track of the `allow_simple_key` flag here. + # Indentation rules are loosed for the flow context. + chunks = [] + start_mark = self.get_mark() + end_mark = start_mark + indent = self.indent+1 + # We allow zero indentation for scalars, but then we need to check for + # document separators at the beginning of the line. + #if indent == 0: + # indent = 1 + spaces = [] + while True: + length = 0 + if self.peek() == '#': + break + while True: + ch = self.peek(length) + if ch in '\0 \t\r\n\x85\u2028\u2029' \ + or (ch == ':' and + self.peek(length+1) in '\0 \t\r\n\x85\u2028\u2029' + + (u',[]{}' if self.flow_level else u''))\ + or (self.flow_level and ch in ',?[]{}'): + break + length += 1 + if length == 0: + break + self.allow_simple_key = False + chunks.extend(spaces) + chunks.append(self.prefix(length)) + self.forward(length) + end_mark = self.get_mark() + spaces = self.scan_plain_spaces(indent, start_mark) + if not spaces or self.peek() == '#' \ + or (not self.flow_level and self.column < indent): + break + return ScalarToken(''.join(chunks), True, start_mark, end_mark) + + def scan_plain_spaces(self, indent, start_mark): + # See the specification for details. + # The specification is really confusing about tabs in plain scalars. + # We just forbid them completely. Do not use tabs in YAML! + chunks = [] + length = 0 + while self.peek(length) in ' ': + length += 1 + whitespaces = self.prefix(length) + self.forward(length) + ch = self.peek() + if ch in '\r\n\x85\u2028\u2029': + line_break = self.scan_line_break() + self.allow_simple_key = True + prefix = self.prefix(3) + if (prefix == '---' or prefix == '...') \ + and self.peek(3) in '\0 \t\r\n\x85\u2028\u2029': + return + breaks = [] + while self.peek() in ' \r\n\x85\u2028\u2029': + if self.peek() == ' ': + self.forward() + else: + breaks.append(self.scan_line_break()) + prefix = self.prefix(3) + if (prefix == '---' or prefix == '...') \ + and self.peek(3) in '\0 \t\r\n\x85\u2028\u2029': + return + if line_break != '\n': + chunks.append(line_break) + elif not breaks: + chunks.append(' ') + chunks.extend(breaks) + elif whitespaces: + chunks.append(whitespaces) + return chunks + + def scan_tag_handle(self, name, start_mark): + # See the specification for details. + # For some strange reasons, the specification does not allow '_' in + # tag handles. I have allowed it anyway. + ch = self.peek() + if ch != '!': + raise ScannerError("while scanning a %s" % name, start_mark, + "expected '!', but found %r" % ch, self.get_mark()) + length = 1 + ch = self.peek(length) + if ch != ' ': + while '0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ + or ch in '-_': + length += 1 + ch = self.peek(length) + if ch != '!': + self.forward(length) + raise ScannerError("while scanning a %s" % name, start_mark, + "expected '!', but found %r" % ch, self.get_mark()) + length += 1 + value = self.prefix(length) + self.forward(length) + return value + + def scan_tag_uri(self, name, start_mark): + # See the specification for details. + # Note: we do not check if URI is well-formed. + chunks = [] + length = 0 + ch = self.peek(length) + while '0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ + or ch in '-;/?:@&=+$,_.!~*\'()[]%': + if ch == '%': + chunks.append(self.prefix(length)) + self.forward(length) + length = 0 + chunks.append(self.scan_uri_escapes(name, start_mark)) + else: + length += 1 + ch = self.peek(length) + if length: + chunks.append(self.prefix(length)) + self.forward(length) + length = 0 + if not chunks: + raise ScannerError("while parsing a %s" % name, start_mark, + "expected URI, but found %r" % ch, self.get_mark()) + return ''.join(chunks) + + def scan_uri_escapes(self, name, start_mark): + # See the specification for details. + codes = [] + mark = self.get_mark() + while self.peek() == '%': + self.forward() + for k in range(2): + if self.peek(k) not in '0123456789ABCDEFabcdef': + raise ScannerError("while scanning a %s" % name, start_mark, + "expected URI escape sequence of 2 hexdecimal numbers, but found %r" + % self.peek(k), self.get_mark()) + codes.append(int(self.prefix(2), 16)) + self.forward(2) + try: + value = bytes(codes).decode('utf-8') + except UnicodeDecodeError as exc: + raise ScannerError("while scanning a %s" % name, start_mark, str(exc), mark) + return value + + def scan_line_break(self): + # Transforms: + # '\r\n' : '\n' + # '\r' : '\n' + # '\n' : '\n' + # '\x85' : '\n' + # '\u2028' : '\u2028' + # '\u2029 : '\u2029' + # default : '' + ch = self.peek() + if ch in '\r\n\x85': + if self.prefix(2) == '\r\n': + self.forward(2) + else: + self.forward() + return '\n' + elif ch in '\u2028\u2029': + self.forward() + return ch + return '' diff --git a/third_party/python/PyYAML/lib3/yaml/serializer.py b/third_party/python/PyYAML/lib3/yaml/serializer.py new file mode 100644 index 0000000000..fe911e67ae --- /dev/null +++ b/third_party/python/PyYAML/lib3/yaml/serializer.py @@ -0,0 +1,111 @@ + +__all__ = ['Serializer', 'SerializerError'] + +from .error import YAMLError +from .events import * +from .nodes import * + +class SerializerError(YAMLError): + pass + +class Serializer: + + ANCHOR_TEMPLATE = 'id%03d' + + def __init__(self, encoding=None, + explicit_start=None, explicit_end=None, version=None, tags=None): + self.use_encoding = encoding + self.use_explicit_start = explicit_start + self.use_explicit_end = explicit_end + self.use_version = version + self.use_tags = tags + self.serialized_nodes = {} + self.anchors = {} + self.last_anchor_id = 0 + self.closed = None + + def open(self): + if self.closed is None: + self.emit(StreamStartEvent(encoding=self.use_encoding)) + self.closed = False + elif self.closed: + raise SerializerError("serializer is closed") + else: + raise SerializerError("serializer is already opened") + + def close(self): + if self.closed is None: + raise SerializerError("serializer is not opened") + elif not self.closed: + self.emit(StreamEndEvent()) + self.closed = True + + #def __del__(self): + # self.close() + + def serialize(self, node): + if self.closed is None: + raise SerializerError("serializer is not opened") + elif self.closed: + raise SerializerError("serializer is closed") + self.emit(DocumentStartEvent(explicit=self.use_explicit_start, + version=self.use_version, tags=self.use_tags)) + self.anchor_node(node) + self.serialize_node(node, None, None) + self.emit(DocumentEndEvent(explicit=self.use_explicit_end)) + self.serialized_nodes = {} + self.anchors = {} + self.last_anchor_id = 0 + + def anchor_node(self, node): + if node in self.anchors: + if self.anchors[node] is None: + self.anchors[node] = self.generate_anchor(node) + else: + self.anchors[node] = None + if isinstance(node, SequenceNode): + for item in node.value: + self.anchor_node(item) + elif isinstance(node, MappingNode): + for key, value in node.value: + self.anchor_node(key) + self.anchor_node(value) + + def generate_anchor(self, node): + self.last_anchor_id += 1 + return self.ANCHOR_TEMPLATE % self.last_anchor_id + + def serialize_node(self, node, parent, index): + alias = self.anchors[node] + if node in self.serialized_nodes: + self.emit(AliasEvent(alias)) + else: + self.serialized_nodes[node] = True + self.descend_resolver(parent, index) + if isinstance(node, ScalarNode): + detected_tag = self.resolve(ScalarNode, node.value, (True, False)) + default_tag = self.resolve(ScalarNode, node.value, (False, True)) + implicit = (node.tag == detected_tag), (node.tag == default_tag) + self.emit(ScalarEvent(alias, node.tag, implicit, node.value, + style=node.style)) + elif isinstance(node, SequenceNode): + implicit = (node.tag + == self.resolve(SequenceNode, node.value, True)) + self.emit(SequenceStartEvent(alias, node.tag, implicit, + flow_style=node.flow_style)) + index = 0 + for item in node.value: + self.serialize_node(item, node, index) + index += 1 + self.emit(SequenceEndEvent()) + elif isinstance(node, MappingNode): + implicit = (node.tag + == self.resolve(MappingNode, node.value, True)) + self.emit(MappingStartEvent(alias, node.tag, implicit, + flow_style=node.flow_style)) + for key, value in node.value: + self.serialize_node(key, node, None) + self.serialize_node(value, node, key) + self.emit(MappingEndEvent()) + self.ascend_resolver() + diff --git a/third_party/python/PyYAML/lib3/yaml/tokens.py b/third_party/python/PyYAML/lib3/yaml/tokens.py new file mode 100644 index 0000000000..4d0b48a394 --- /dev/null +++ b/third_party/python/PyYAML/lib3/yaml/tokens.py @@ -0,0 +1,104 @@ + +class Token(object): + def __init__(self, start_mark, end_mark): + self.start_mark = start_mark + self.end_mark = end_mark + def __repr__(self): + attributes = [key for key in self.__dict__ + if not key.endswith('_mark')] + attributes.sort() + arguments = ', '.join(['%s=%r' % (key, getattr(self, key)) + for key in attributes]) + return '%s(%s)' % (self.__class__.__name__, arguments) + +#class BOMToken(Token): +# id = '' + +class DirectiveToken(Token): + id = '' + def __init__(self, name, value, start_mark, end_mark): + self.name = name + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + +class DocumentStartToken(Token): + id = '' + +class DocumentEndToken(Token): + id = '' + +class StreamStartToken(Token): + id = '' + def __init__(self, start_mark=None, end_mark=None, + encoding=None): + self.start_mark = start_mark + self.end_mark = end_mark + self.encoding = encoding + +class StreamEndToken(Token): + id = '' + +class BlockSequenceStartToken(Token): + id = '' + +class BlockMappingStartToken(Token): + id = '' + +class BlockEndToken(Token): + id = '' + +class FlowSequenceStartToken(Token): + id = '[' + +class FlowMappingStartToken(Token): + id = '{' + +class FlowSequenceEndToken(Token): + id = ']' + +class FlowMappingEndToken(Token): + id = '}' + +class KeyToken(Token): + id = '?' + +class ValueToken(Token): + id = ':' + +class BlockEntryToken(Token): + id = '-' + +class FlowEntryToken(Token): + id = ',' + +class AliasToken(Token): + id = '' + def __init__(self, value, start_mark, end_mark): + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + +class AnchorToken(Token): + id = '' + def __init__(self, value, start_mark, end_mark): + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + +class TagToken(Token): + id = '' + def __init__(self, value, start_mark, end_mark): + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + +class ScalarToken(Token): + id = '' + def __init__(self, value, plain, start_mark, end_mark, style=None): + self.value = value + self.plain = plain + self.start_mark = start_mark + self.end_mark = end_mark + self.style = style + diff --git a/third_party/python/PyYAML/pyproject.toml b/third_party/python/PyYAML/pyproject.toml new file mode 100644 index 0000000000..2bf5ec8096 --- /dev/null +++ b/third_party/python/PyYAML/pyproject.toml @@ -0,0 +1,3 @@ +[build-system] +requires = ["setuptools", "wheel", "Cython"] +build-backend = "setuptools.build_meta" diff --git a/third_party/python/PyYAML/setup.cfg b/third_party/python/PyYAML/setup.cfg new file mode 100644 index 0000000000..da51366b86 --- /dev/null +++ b/third_party/python/PyYAML/setup.cfg @@ -0,0 +1,9 @@ +[build_ext] + +[metadata] +license_file = LICENSE + +[egg_info] +tag_build = +tag_date = 0 + diff --git a/third_party/python/PyYAML/setup.py b/third_party/python/PyYAML/setup.py new file mode 100644 index 0000000000..d7476c61c6 --- /dev/null +++ b/third_party/python/PyYAML/setup.py @@ -0,0 +1,296 @@ + +NAME = 'PyYAML' +VERSION = '5.4.1' +DESCRIPTION = "YAML parser and emitter for Python" +LONG_DESCRIPTION = """\ +YAML is a data serialization format designed for human readability +and interaction with scripting languages. PyYAML is a YAML parser +and emitter for Python. + +PyYAML features a complete YAML 1.1 parser, Unicode support, pickle +support, capable extension API, and sensible error messages. PyYAML +supports standard YAML tags and provides Python-specific tags that +allow to represent an arbitrary Python object. + +PyYAML is applicable for a broad range of tasks from complex +configuration files to object serialization and persistence.""" +AUTHOR = "Kirill Simonov" +AUTHOR_EMAIL = 'xi@resolvent.net' +LICENSE = "MIT" +PLATFORMS = "Any" +URL = "https://pyyaml.org/" +DOWNLOAD_URL = "https://pypi.org/project/PyYAML/" +CLASSIFIERS = [ + "Development Status :: 5 - Production/Stable", + "Intended Audience :: Developers", + "License :: OSI Approved :: MIT License", + "Operating System :: OS Independent", + "Programming Language :: Cython", + "Programming Language :: Python", + "Programming Language :: Python :: 2", + "Programming Language :: Python :: 2.7", + "Programming Language :: Python :: 3", + "Programming Language :: Python :: 3.6", + "Programming Language :: Python :: 3.7", + "Programming Language :: Python :: 3.8", + "Programming Language :: Python :: 3.9", + "Programming Language :: Python :: Implementation :: CPython", + "Programming Language :: Python :: Implementation :: PyPy", + "Topic :: Software Development :: Libraries :: Python Modules", + "Topic :: Text Processing :: Markup", +] +PROJECT_URLS = { + 'Bug Tracker': 'https://github.com/yaml/pyyaml/issues', + 'CI': 'https://github.com/yaml/pyyaml/actions', + 'Documentation': 'https://pyyaml.org/wiki/PyYAMLDocumentation', + 'Mailing lists': 'http://lists.sourceforge.net/lists/listinfo/yaml-core', + 'Source Code': 'https://github.com/yaml/pyyaml', +} + +LIBYAML_CHECK = """ +#include + +int main(void) { + yaml_parser_t parser; + yaml_emitter_t emitter; + + yaml_parser_initialize(&parser); + yaml_parser_delete(&parser); + + yaml_emitter_initialize(&emitter); + yaml_emitter_delete(&emitter); + + return 0; +} +""" + + +import sys, os, os.path, platform, warnings + +from distutils import log +from setuptools import setup, Command, Distribution as _Distribution, Extension as _Extension +from setuptools.command.build_ext import build_ext as _build_ext +from distutils.errors import DistutilsError, CompileError, LinkError, DistutilsPlatformError + +with_cython = False +if 'sdist' in sys.argv or os.environ.get('PYYAML_FORCE_CYTHON') == '1': + # we need cython here + with_cython = True +try: + from Cython.Distutils.extension import Extension as _Extension + from Cython.Distutils import build_ext as _build_ext + with_cython = True +except ImportError: + if with_cython: + raise + +try: + from wheel.bdist_wheel import bdist_wheel +except ImportError: + bdist_wheel = None + + +# on Windows, disable wheel generation warning noise +windows_ignore_warnings = [ +"Unknown distribution option: 'python_requires'", +"Config variable 'Py_DEBUG' is unset", +"Config variable 'WITH_PYMALLOC' is unset", +"Config variable 'Py_UNICODE_SIZE' is unset", +"Cython directive 'language_level' not set" +] + +if platform.system() == 'Windows': + for w in windows_ignore_warnings: + warnings.filterwarnings('ignore', w) + + +class Distribution(_Distribution): + def __init__(self, attrs=None): + _Distribution.__init__(self, attrs) + if not self.ext_modules: + return + for idx in range(len(self.ext_modules)-1, -1, -1): + ext = self.ext_modules[idx] + if not isinstance(ext, Extension): + continue + setattr(self, ext.attr_name, None) + self.global_options = [ + (ext.option_name, None, + "include %s (default if %s is available)" + % (ext.feature_description, ext.feature_name)), + (ext.neg_option_name, None, + "exclude %s" % ext.feature_description), + ] + self.global_options + self.negative_opt = self.negative_opt.copy() + self.negative_opt[ext.neg_option_name] = ext.option_name + + def has_ext_modules(self): + if not self.ext_modules: + return False + for ext in self.ext_modules: + with_ext = self.ext_status(ext) + if with_ext is None or with_ext: + return True + return False + + def ext_status(self, ext): + implementation = platform.python_implementation() + if implementation not in ['CPython', 'PyPy']: + return False + if isinstance(ext, Extension): + # the "build by default" behavior is implemented by this returning None + with_ext = getattr(self, ext.attr_name) or os.environ.get('PYYAML_FORCE_{0}'.format(ext.feature_name.upper())) + try: + with_ext = int(with_ext) # attempt coerce envvar to int + except TypeError: + pass + return with_ext + else: + return True + + +class Extension(_Extension): + + def __init__(self, name, sources, feature_name, feature_description, + feature_check, **kwds): + if not with_cython: + for filename in sources[:]: + base, ext = os.path.splitext(filename) + if ext == '.pyx': + sources.remove(filename) + sources.append('%s.c' % base) + _Extension.__init__(self, name, sources, **kwds) + self.feature_name = feature_name + self.feature_description = feature_description + self.feature_check = feature_check + self.attr_name = 'with_' + feature_name.replace('-', '_') + self.option_name = 'with-' + feature_name + self.neg_option_name = 'without-' + feature_name + + +class build_ext(_build_ext): + + def run(self): + optional = True + disabled = True + for ext in self.extensions: + with_ext = self.distribution.ext_status(ext) + if with_ext is None: + disabled = False + elif with_ext: + optional = False + disabled = False + break + if disabled: + return + try: + _build_ext.run(self) + except DistutilsPlatformError: + exc = sys.exc_info()[1] + if optional: + log.warn(str(exc)) + log.warn("skipping build_ext") + else: + raise + + def get_source_files(self): + self.check_extensions_list(self.extensions) + filenames = [] + for ext in self.extensions: + if with_cython: + self.cython_sources(ext.sources, ext) + for filename in ext.sources: + filenames.append(filename) + base = os.path.splitext(filename)[0] + for ext in ['c', 'h', 'pyx', 'pxd']: + filename = '%s.%s' % (base, ext) + if filename not in filenames and os.path.isfile(filename): + filenames.append(filename) + return filenames + + def get_outputs(self): + self.check_extensions_list(self.extensions) + outputs = [] + for ext in self.extensions: + fullname = self.get_ext_fullname(ext.name) + filename = os.path.join(self.build_lib, + self.get_ext_filename(fullname)) + if os.path.isfile(filename): + outputs.append(filename) + return outputs + + def build_extensions(self): + self.check_extensions_list(self.extensions) + for ext in self.extensions: + with_ext = self.distribution.ext_status(ext) + if with_ext is not None and not with_ext: + continue + if with_cython: + ext.sources = self.cython_sources(ext.sources, ext) + try: + self.build_extension(ext) + except (CompileError, LinkError): + if with_ext is not None: + raise + log.warn("Error compiling module, falling back to pure Python") + + +class test(Command): + + user_options = [] + + def initialize_options(self): + pass + + def finalize_options(self): + pass + + def run(self): + build_cmd = self.get_finalized_command('build') + build_cmd.run() + sys.path.insert(0, build_cmd.build_lib) + if sys.version_info[0] < 3: + sys.path.insert(0, 'tests/lib') + else: + sys.path.insert(0, 'tests/lib3') + import test_all + if not test_all.main([]): + raise DistutilsError("Tests failed") + + +cmdclass = { + 'build_ext': build_ext, + 'test': test, +} +if bdist_wheel: + cmdclass['bdist_wheel'] = bdist_wheel + + +if __name__ == '__main__': + + setup( + name=NAME, + version=VERSION, + description=DESCRIPTION, + long_description=LONG_DESCRIPTION, + author=AUTHOR, + author_email=AUTHOR_EMAIL, + license=LICENSE, + platforms=PLATFORMS, + url=URL, + download_url=DOWNLOAD_URL, + classifiers=CLASSIFIERS, + project_urls=PROJECT_URLS, + + package_dir={'': {2: 'lib', 3: 'lib3'}[sys.version_info[0]]}, + packages=['yaml', '_yaml'], + ext_modules=[ + Extension('yaml._yaml', ['yaml/_yaml.pyx'], + 'libyaml', "LibYAML bindings", LIBYAML_CHECK, + libraries=['yaml']), + ], + + distclass=Distribution, + cmdclass=cmdclass, + python_requires='>=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*', + ) diff --git a/third_party/python/PyYAML/yaml/__init__.pxd b/third_party/python/PyYAML/yaml/__init__.pxd new file mode 100644 index 0000000000..e69de29bb2 diff --git a/third_party/python/PyYAML/yaml/_yaml.h b/third_party/python/PyYAML/yaml/_yaml.h new file mode 100644 index 0000000000..21fd6a991b --- /dev/null +++ b/third_party/python/PyYAML/yaml/_yaml.h @@ -0,0 +1,23 @@ + +#include + +#if PY_MAJOR_VERSION < 3 + +#define PyUnicode_FromString(s) PyUnicode_DecodeUTF8((s), strlen(s), "strict") + +#else + +#define PyString_CheckExact PyBytes_CheckExact +#define PyString_AS_STRING PyBytes_AS_STRING +#define PyString_GET_SIZE PyBytes_GET_SIZE +#define PyString_FromStringAndSize PyBytes_FromStringAndSize + +#endif + +#ifdef _MSC_VER /* MS Visual C++ 6.0 */ +#if _MSC_VER == 1200 + +#define PyLong_FromUnsignedLongLong(z) PyInt_FromLong(i) + +#endif +#endif diff --git a/third_party/python/PyYAML/yaml/_yaml.pxd b/third_party/python/PyYAML/yaml/_yaml.pxd new file mode 100644 index 0000000000..7937c9db51 --- /dev/null +++ b/third_party/python/PyYAML/yaml/_yaml.pxd @@ -0,0 +1,251 @@ + +cdef extern from "_yaml.h": + + void malloc(int l) + void memcpy(char *d, char *s, int l) + int strlen(char *s) + int PyString_CheckExact(object o) + int PyUnicode_CheckExact(object o) + char *PyString_AS_STRING(object o) + int PyString_GET_SIZE(object o) + object PyString_FromStringAndSize(char *v, int l) + object PyUnicode_FromString(char *u) + object PyUnicode_DecodeUTF8(char *u, int s, char *e) + object PyUnicode_AsUTF8String(object o) + int PY_MAJOR_VERSION + + ctypedef enum: + SIZEOF_VOID_P + ctypedef enum yaml_encoding_t: + YAML_ANY_ENCODING + YAML_UTF8_ENCODING + YAML_UTF16LE_ENCODING + YAML_UTF16BE_ENCODING + ctypedef enum yaml_break_t: + YAML_ANY_BREAK + YAML_CR_BREAK + YAML_LN_BREAK + YAML_CRLN_BREAK + ctypedef enum yaml_error_type_t: + YAML_NO_ERROR + YAML_MEMORY_ERROR + YAML_READER_ERROR + YAML_SCANNER_ERROR + YAML_PARSER_ERROR + YAML_WRITER_ERROR + YAML_EMITTER_ERROR + ctypedef enum yaml_scalar_style_t: + YAML_ANY_SCALAR_STYLE + YAML_PLAIN_SCALAR_STYLE + YAML_SINGLE_QUOTED_SCALAR_STYLE + YAML_DOUBLE_QUOTED_SCALAR_STYLE + YAML_LITERAL_SCALAR_STYLE + YAML_FOLDED_SCALAR_STYLE + ctypedef enum yaml_sequence_style_t: + YAML_ANY_SEQUENCE_STYLE + YAML_BLOCK_SEQUENCE_STYLE + YAML_FLOW_SEQUENCE_STYLE + ctypedef enum yaml_mapping_style_t: + YAML_ANY_MAPPING_STYLE + YAML_BLOCK_MAPPING_STYLE + YAML_FLOW_MAPPING_STYLE + ctypedef enum yaml_token_type_t: + YAML_NO_TOKEN + YAML_STREAM_START_TOKEN + YAML_STREAM_END_TOKEN + YAML_VERSION_DIRECTIVE_TOKEN + YAML_TAG_DIRECTIVE_TOKEN + YAML_DOCUMENT_START_TOKEN + YAML_DOCUMENT_END_TOKEN + YAML_BLOCK_SEQUENCE_START_TOKEN + YAML_BLOCK_MAPPING_START_TOKEN + YAML_BLOCK_END_TOKEN + YAML_FLOW_SEQUENCE_START_TOKEN + YAML_FLOW_SEQUENCE_END_TOKEN + YAML_FLOW_MAPPING_START_TOKEN + YAML_FLOW_MAPPING_END_TOKEN + YAML_BLOCK_ENTRY_TOKEN + YAML_FLOW_ENTRY_TOKEN + YAML_KEY_TOKEN + YAML_VALUE_TOKEN + YAML_ALIAS_TOKEN + YAML_ANCHOR_TOKEN + YAML_TAG_TOKEN + YAML_SCALAR_TOKEN + ctypedef enum yaml_event_type_t: + YAML_NO_EVENT + YAML_STREAM_START_EVENT + YAML_STREAM_END_EVENT + YAML_DOCUMENT_START_EVENT + YAML_DOCUMENT_END_EVENT + YAML_ALIAS_EVENT + YAML_SCALAR_EVENT + YAML_SEQUENCE_START_EVENT + YAML_SEQUENCE_END_EVENT + YAML_MAPPING_START_EVENT + YAML_MAPPING_END_EVENT + + ctypedef int yaml_read_handler_t(void *data, char *buffer, + size_t size, size_t *size_read) except 0 + + ctypedef int yaml_write_handler_t(void *data, char *buffer, + size_t size) except 0 + + ctypedef struct yaml_mark_t: + size_t index + size_t line + size_t column + ctypedef struct yaml_version_directive_t: + int major + int minor + ctypedef struct yaml_tag_directive_t: + char *handle + char *prefix + + ctypedef struct _yaml_token_stream_start_data_t: + yaml_encoding_t encoding + ctypedef struct _yaml_token_alias_data_t: + char *value + ctypedef struct _yaml_token_anchor_data_t: + char *value + ctypedef struct _yaml_token_tag_data_t: + char *handle + char *suffix + ctypedef struct _yaml_token_scalar_data_t: + char *value + size_t length + yaml_scalar_style_t style + ctypedef struct _yaml_token_version_directive_data_t: + int major + int minor + ctypedef struct _yaml_token_tag_directive_data_t: + char *handle + char *prefix + ctypedef union _yaml_token_data_t: + _yaml_token_stream_start_data_t stream_start + _yaml_token_alias_data_t alias + _yaml_token_anchor_data_t anchor + _yaml_token_tag_data_t tag + _yaml_token_scalar_data_t scalar + _yaml_token_version_directive_data_t version_directive + _yaml_token_tag_directive_data_t tag_directive + ctypedef struct yaml_token_t: + yaml_token_type_t type + _yaml_token_data_t data + yaml_mark_t start_mark + yaml_mark_t end_mark + + ctypedef struct _yaml_event_stream_start_data_t: + yaml_encoding_t encoding + ctypedef struct _yaml_event_document_start_data_tag_directives_t: + yaml_tag_directive_t *start + yaml_tag_directive_t *end + ctypedef struct _yaml_event_document_start_data_t: + yaml_version_directive_t *version_directive + _yaml_event_document_start_data_tag_directives_t tag_directives + int implicit + ctypedef struct _yaml_event_document_end_data_t: + int implicit + ctypedef struct _yaml_event_alias_data_t: + char *anchor + ctypedef struct _yaml_event_scalar_data_t: + char *anchor + char *tag + char *value + size_t length + int plain_implicit + int quoted_implicit + yaml_scalar_style_t style + ctypedef struct _yaml_event_sequence_start_data_t: + char *anchor + char *tag + int implicit + yaml_sequence_style_t style + ctypedef struct _yaml_event_mapping_start_data_t: + char *anchor + char *tag + int implicit + yaml_mapping_style_t style + ctypedef union _yaml_event_data_t: + _yaml_event_stream_start_data_t stream_start + _yaml_event_document_start_data_t document_start + _yaml_event_document_end_data_t document_end + _yaml_event_alias_data_t alias + _yaml_event_scalar_data_t scalar + _yaml_event_sequence_start_data_t sequence_start + _yaml_event_mapping_start_data_t mapping_start + ctypedef struct yaml_event_t: + yaml_event_type_t type + _yaml_event_data_t data + yaml_mark_t start_mark + yaml_mark_t end_mark + + ctypedef struct yaml_parser_t: + yaml_error_type_t error + char *problem + size_t problem_offset + int problem_value + yaml_mark_t problem_mark + char *context + yaml_mark_t context_mark + + ctypedef struct yaml_emitter_t: + yaml_error_type_t error + char *problem + + char *yaml_get_version_string() + void yaml_get_version(int *major, int *minor, int *patch) + + void yaml_token_delete(yaml_token_t *token) + + int yaml_stream_start_event_initialize(yaml_event_t *event, + yaml_encoding_t encoding) + int yaml_stream_end_event_initialize(yaml_event_t *event) + int yaml_document_start_event_initialize(yaml_event_t *event, + yaml_version_directive_t *version_directive, + yaml_tag_directive_t *tag_directives_start, + yaml_tag_directive_t *tag_directives_end, + int implicit) + int yaml_document_end_event_initialize(yaml_event_t *event, + int implicit) + int yaml_alias_event_initialize(yaml_event_t *event, char *anchor) + int yaml_scalar_event_initialize(yaml_event_t *event, + char *anchor, char *tag, char *value, size_t length, + int plain_implicit, int quoted_implicit, + yaml_scalar_style_t style) + int yaml_sequence_start_event_initialize(yaml_event_t *event, + char *anchor, char *tag, int implicit, yaml_sequence_style_t style) + int yaml_sequence_end_event_initialize(yaml_event_t *event) + int yaml_mapping_start_event_initialize(yaml_event_t *event, + char *anchor, char *tag, int implicit, yaml_mapping_style_t style) + int yaml_mapping_end_event_initialize(yaml_event_t *event) + void yaml_event_delete(yaml_event_t *event) + + int yaml_parser_initialize(yaml_parser_t *parser) + void yaml_parser_delete(yaml_parser_t *parser) + void yaml_parser_set_input_string(yaml_parser_t *parser, + char *input, size_t size) + void yaml_parser_set_input(yaml_parser_t *parser, + yaml_read_handler_t *handler, void *data) + void yaml_parser_set_encoding(yaml_parser_t *parser, + yaml_encoding_t encoding) + int yaml_parser_scan(yaml_parser_t *parser, yaml_token_t *token) except * + int yaml_parser_parse(yaml_parser_t *parser, yaml_event_t *event) except * + + int yaml_emitter_initialize(yaml_emitter_t *emitter) + void yaml_emitter_delete(yaml_emitter_t *emitter) + void yaml_emitter_set_output_string(yaml_emitter_t *emitter, + char *output, size_t size, size_t *size_written) + void yaml_emitter_set_output(yaml_emitter_t *emitter, + yaml_write_handler_t *handler, void *data) + void yaml_emitter_set_encoding(yaml_emitter_t *emitter, + yaml_encoding_t encoding) + void yaml_emitter_set_canonical(yaml_emitter_t *emitter, int canonical) + void yaml_emitter_set_indent(yaml_emitter_t *emitter, int indent) + void yaml_emitter_set_width(yaml_emitter_t *emitter, int width) + void yaml_emitter_set_unicode(yaml_emitter_t *emitter, int unicode) + void yaml_emitter_set_break(yaml_emitter_t *emitter, + yaml_break_t line_break) + int yaml_emitter_emit(yaml_emitter_t *emitter, yaml_event_t *event) except * + int yaml_emitter_flush(yaml_emitter_t *emitter) + diff --git a/third_party/python/PyYAML/yaml/_yaml.pyx b/third_party/python/PyYAML/yaml/_yaml.pyx new file mode 100644 index 0000000000..ff4efe80b5 --- /dev/null +++ b/third_party/python/PyYAML/yaml/_yaml.pyx @@ -0,0 +1,1527 @@ + +import yaml + +def get_version_string(): + cdef char *value + value = yaml_get_version_string() + if PY_MAJOR_VERSION < 3: + return value + else: + return PyUnicode_FromString(value) + +def get_version(): + cdef int major, minor, patch + yaml_get_version(&major, &minor, &patch) + return (major, minor, patch) + +#Mark = yaml.error.Mark +YAMLError = yaml.error.YAMLError +ReaderError = yaml.reader.ReaderError +ScannerError = yaml.scanner.ScannerError +ParserError = yaml.parser.ParserError +ComposerError = yaml.composer.ComposerError +ConstructorError = yaml.constructor.ConstructorError +EmitterError = yaml.emitter.EmitterError +SerializerError = yaml.serializer.SerializerError +RepresenterError = yaml.representer.RepresenterError + +StreamStartToken = yaml.tokens.StreamStartToken +StreamEndToken = yaml.tokens.StreamEndToken +DirectiveToken = yaml.tokens.DirectiveToken +DocumentStartToken = yaml.tokens.DocumentStartToken +DocumentEndToken = yaml.tokens.DocumentEndToken +BlockSequenceStartToken = yaml.tokens.BlockSequenceStartToken +BlockMappingStartToken = yaml.tokens.BlockMappingStartToken +BlockEndToken = yaml.tokens.BlockEndToken +FlowSequenceStartToken = yaml.tokens.FlowSequenceStartToken +FlowMappingStartToken = yaml.tokens.FlowMappingStartToken +FlowSequenceEndToken = yaml.tokens.FlowSequenceEndToken +FlowMappingEndToken = yaml.tokens.FlowMappingEndToken +KeyToken = yaml.tokens.KeyToken +ValueToken = yaml.tokens.ValueToken +BlockEntryToken = yaml.tokens.BlockEntryToken +FlowEntryToken = yaml.tokens.FlowEntryToken +AliasToken = yaml.tokens.AliasToken +AnchorToken = yaml.tokens.AnchorToken +TagToken = yaml.tokens.TagToken +ScalarToken = yaml.tokens.ScalarToken + +StreamStartEvent = yaml.events.StreamStartEvent +StreamEndEvent = yaml.events.StreamEndEvent +DocumentStartEvent = yaml.events.DocumentStartEvent +DocumentEndEvent = yaml.events.DocumentEndEvent +AliasEvent = yaml.events.AliasEvent +ScalarEvent = yaml.events.ScalarEvent +SequenceStartEvent = yaml.events.SequenceStartEvent +SequenceEndEvent = yaml.events.SequenceEndEvent +MappingStartEvent = yaml.events.MappingStartEvent +MappingEndEvent = yaml.events.MappingEndEvent + +ScalarNode = yaml.nodes.ScalarNode +SequenceNode = yaml.nodes.SequenceNode +MappingNode = yaml.nodes.MappingNode + +cdef class Mark: + cdef readonly object name + cdef readonly size_t index + cdef readonly size_t line + cdef readonly size_t column + cdef readonly buffer + cdef readonly pointer + + def __init__(self, object name, size_t index, size_t line, size_t column, + object buffer, object pointer): + self.name = name + self.index = index + self.line = line + self.column = column + self.buffer = buffer + self.pointer = pointer + + def get_snippet(self): + return None + + def __str__(self): + where = " in \"%s\", line %d, column %d" \ + % (self.name, self.line+1, self.column+1) + return where + +#class YAMLError(Exception): +# pass +# +#class MarkedYAMLError(YAMLError): +# +# def __init__(self, context=None, context_mark=None, +# problem=None, problem_mark=None, note=None): +# self.context = context +# self.context_mark = context_mark +# self.problem = problem +# self.problem_mark = problem_mark +# self.note = note +# +# def __str__(self): +# lines = [] +# if self.context is not None: +# lines.append(self.context) +# if self.context_mark is not None \ +# and (self.problem is None or self.problem_mark is None +# or self.context_mark.name != self.problem_mark.name +# or self.context_mark.line != self.problem_mark.line +# or self.context_mark.column != self.problem_mark.column): +# lines.append(str(self.context_mark)) +# if self.problem is not None: +# lines.append(self.problem) +# if self.problem_mark is not None: +# lines.append(str(self.problem_mark)) +# if self.note is not None: +# lines.append(self.note) +# return '\n'.join(lines) +# +#class ReaderError(YAMLError): +# +# def __init__(self, name, position, character, encoding, reason): +# self.name = name +# self.character = character +# self.position = position +# self.encoding = encoding +# self.reason = reason +# +# def __str__(self): +# if isinstance(self.character, str): +# return "'%s' codec can't decode byte #x%02x: %s\n" \ +# " in \"%s\", position %d" \ +# % (self.encoding, ord(self.character), self.reason, +# self.name, self.position) +# else: +# return "unacceptable character #x%04x: %s\n" \ +# " in \"%s\", position %d" \ +# % (ord(self.character), self.reason, +# self.name, self.position) +# +#class ScannerError(MarkedYAMLError): +# pass +# +#class ParserError(MarkedYAMLError): +# pass +# +#class EmitterError(YAMLError): +# pass +# +#cdef class Token: +# cdef readonly Mark start_mark +# cdef readonly Mark end_mark +# def __init__(self, Mark start_mark, Mark end_mark): +# self.start_mark = start_mark +# self.end_mark = end_mark +# +#cdef class StreamStartToken(Token): +# cdef readonly object encoding +# def __init__(self, Mark start_mark, Mark end_mark, encoding): +# self.start_mark = start_mark +# self.end_mark = end_mark +# self.encoding = encoding +# +#cdef class StreamEndToken(Token): +# pass +# +#cdef class DirectiveToken(Token): +# cdef readonly object name +# cdef readonly object value +# def __init__(self, name, value, Mark start_mark, Mark end_mark): +# self.name = name +# self.value = value +# self.start_mark = start_mark +# self.end_mark = end_mark +# +#cdef class DocumentStartToken(Token): +# pass +# +#cdef class DocumentEndToken(Token): +# pass +# +#cdef class BlockSequenceStartToken(Token): +# pass +# +#cdef class BlockMappingStartToken(Token): +# pass +# +#cdef class BlockEndToken(Token): +# pass +# +#cdef class FlowSequenceStartToken(Token): +# pass +# +#cdef class FlowMappingStartToken(Token): +# pass +# +#cdef class FlowSequenceEndToken(Token): +# pass +# +#cdef class FlowMappingEndToken(Token): +# pass +# +#cdef class KeyToken(Token): +# pass +# +#cdef class ValueToken(Token): +# pass +# +#cdef class BlockEntryToken(Token): +# pass +# +#cdef class FlowEntryToken(Token): +# pass +# +#cdef class AliasToken(Token): +# cdef readonly object value +# def __init__(self, value, Mark start_mark, Mark end_mark): +# self.value = value +# self.start_mark = start_mark +# self.end_mark = end_mark +# +#cdef class AnchorToken(Token): +# cdef readonly object value +# def __init__(self, value, Mark start_mark, Mark end_mark): +# self.value = value +# self.start_mark = start_mark +# self.end_mark = end_mark +# +#cdef class TagToken(Token): +# cdef readonly object value +# def __init__(self, value, Mark start_mark, Mark end_mark): +# self.value = value +# self.start_mark = start_mark +# self.end_mark = end_mark +# +#cdef class ScalarToken(Token): +# cdef readonly object value +# cdef readonly object plain +# cdef readonly object style +# def __init__(self, value, plain, Mark start_mark, Mark end_mark, style=None): +# self.value = value +# self.plain = plain +# self.start_mark = start_mark +# self.end_mark = end_mark +# self.style = style + +cdef class CParser: + + cdef yaml_parser_t parser + cdef yaml_event_t parsed_event + + cdef object stream + cdef object stream_name + cdef object current_token + cdef object current_event + cdef object anchors + cdef object stream_cache + cdef int stream_cache_len + cdef int stream_cache_pos + cdef int unicode_source + + def __init__(self, stream): + cdef is_readable + if yaml_parser_initialize(&self.parser) == 0: + raise MemoryError + self.parsed_event.type = YAML_NO_EVENT + is_readable = 1 + try: + stream.read + except AttributeError: + is_readable = 0 + self.unicode_source = 0 + if is_readable: + self.stream = stream + try: + self.stream_name = stream.name + except AttributeError: + if PY_MAJOR_VERSION < 3: + self.stream_name = '' + else: + self.stream_name = u'' + self.stream_cache = None + self.stream_cache_len = 0 + self.stream_cache_pos = 0 + yaml_parser_set_input(&self.parser, input_handler, self) + else: + if PyUnicode_CheckExact(stream) != 0: + stream = PyUnicode_AsUTF8String(stream) + if PY_MAJOR_VERSION < 3: + self.stream_name = '' + else: + self.stream_name = u'' + self.unicode_source = 1 + else: + if PY_MAJOR_VERSION < 3: + self.stream_name = '' + else: + self.stream_name = u'' + if PyString_CheckExact(stream) == 0: + if PY_MAJOR_VERSION < 3: + raise TypeError("a string or stream input is required") + else: + raise TypeError(u"a string or stream input is required") + self.stream = stream + yaml_parser_set_input_string(&self.parser, PyString_AS_STRING(stream), PyString_GET_SIZE(stream)) + self.current_token = None + self.current_event = None + self.anchors = {} + + def __dealloc__(self): + yaml_parser_delete(&self.parser) + yaml_event_delete(&self.parsed_event) + + def dispose(self): + pass + + cdef object _parser_error(self): + if self.parser.error == YAML_MEMORY_ERROR: + return MemoryError + elif self.parser.error == YAML_READER_ERROR: + if PY_MAJOR_VERSION < 3: + return ReaderError(self.stream_name, self.parser.problem_offset, + self.parser.problem_value, '?', self.parser.problem) + else: + return ReaderError(self.stream_name, self.parser.problem_offset, + self.parser.problem_value, u'?', PyUnicode_FromString(self.parser.problem)) + elif self.parser.error == YAML_SCANNER_ERROR \ + or self.parser.error == YAML_PARSER_ERROR: + context_mark = None + problem_mark = None + if self.parser.context != NULL: + context_mark = Mark(self.stream_name, + self.parser.context_mark.index, + self.parser.context_mark.line, + self.parser.context_mark.column, None, None) + if self.parser.problem != NULL: + problem_mark = Mark(self.stream_name, + self.parser.problem_mark.index, + self.parser.problem_mark.line, + self.parser.problem_mark.column, None, None) + context = None + if self.parser.context != NULL: + if PY_MAJOR_VERSION < 3: + context = self.parser.context + else: + context = PyUnicode_FromString(self.parser.context) + if PY_MAJOR_VERSION < 3: + problem = self.parser.problem + else: + problem = PyUnicode_FromString(self.parser.problem) + if self.parser.error == YAML_SCANNER_ERROR: + return ScannerError(context, context_mark, problem, problem_mark) + else: + return ParserError(context, context_mark, problem, problem_mark) + if PY_MAJOR_VERSION < 3: + raise ValueError("no parser error") + else: + raise ValueError(u"no parser error") + + def raw_scan(self): + cdef yaml_token_t token + cdef int done + cdef int count + count = 0 + done = 0 + while done == 0: + if yaml_parser_scan(&self.parser, &token) == 0: + error = self._parser_error() + raise error + if token.type == YAML_NO_TOKEN: + done = 1 + else: + count = count+1 + yaml_token_delete(&token) + return count + + cdef object _scan(self): + cdef yaml_token_t token + if yaml_parser_scan(&self.parser, &token) == 0: + error = self._parser_error() + raise error + token_object = self._token_to_object(&token) + yaml_token_delete(&token) + return token_object + + cdef object _token_to_object(self, yaml_token_t *token): + start_mark = Mark(self.stream_name, + token.start_mark.index, + token.start_mark.line, + token.start_mark.column, + None, None) + end_mark = Mark(self.stream_name, + token.end_mark.index, + token.end_mark.line, + token.end_mark.column, + None, None) + if token.type == YAML_NO_TOKEN: + return None + elif token.type == YAML_STREAM_START_TOKEN: + encoding = None + if token.data.stream_start.encoding == YAML_UTF8_ENCODING: + if self.unicode_source == 0: + encoding = u"utf-8" + elif token.data.stream_start.encoding == YAML_UTF16LE_ENCODING: + encoding = u"utf-16-le" + elif token.data.stream_start.encoding == YAML_UTF16BE_ENCODING: + encoding = u"utf-16-be" + return StreamStartToken(start_mark, end_mark, encoding) + elif token.type == YAML_STREAM_END_TOKEN: + return StreamEndToken(start_mark, end_mark) + elif token.type == YAML_VERSION_DIRECTIVE_TOKEN: + return DirectiveToken(u"YAML", + (token.data.version_directive.major, + token.data.version_directive.minor), + start_mark, end_mark) + elif token.type == YAML_TAG_DIRECTIVE_TOKEN: + handle = PyUnicode_FromString(token.data.tag_directive.handle) + prefix = PyUnicode_FromString(token.data.tag_directive.prefix) + return DirectiveToken(u"TAG", (handle, prefix), + start_mark, end_mark) + elif token.type == YAML_DOCUMENT_START_TOKEN: + return DocumentStartToken(start_mark, end_mark) + elif token.type == YAML_DOCUMENT_END_TOKEN: + return DocumentEndToken(start_mark, end_mark) + elif token.type == YAML_BLOCK_SEQUENCE_START_TOKEN: + return BlockSequenceStartToken(start_mark, end_mark) + elif token.type == YAML_BLOCK_MAPPING_START_TOKEN: + return BlockMappingStartToken(start_mark, end_mark) + elif token.type == YAML_BLOCK_END_TOKEN: + return BlockEndToken(start_mark, end_mark) + elif token.type == YAML_FLOW_SEQUENCE_START_TOKEN: + return FlowSequenceStartToken(start_mark, end_mark) + elif token.type == YAML_FLOW_SEQUENCE_END_TOKEN: + return FlowSequenceEndToken(start_mark, end_mark) + elif token.type == YAML_FLOW_MAPPING_START_TOKEN: + return FlowMappingStartToken(start_mark, end_mark) + elif token.type == YAML_FLOW_MAPPING_END_TOKEN: + return FlowMappingEndToken(start_mark, end_mark) + elif token.type == YAML_BLOCK_ENTRY_TOKEN: + return BlockEntryToken(start_mark, end_mark) + elif token.type == YAML_FLOW_ENTRY_TOKEN: + return FlowEntryToken(start_mark, end_mark) + elif token.type == YAML_KEY_TOKEN: + return KeyToken(start_mark, end_mark) + elif token.type == YAML_VALUE_TOKEN: + return ValueToken(start_mark, end_mark) + elif token.type == YAML_ALIAS_TOKEN: + value = PyUnicode_FromString(token.data.alias.value) + return AliasToken(value, start_mark, end_mark) + elif token.type == YAML_ANCHOR_TOKEN: + value = PyUnicode_FromString(token.data.anchor.value) + return AnchorToken(value, start_mark, end_mark) + elif token.type == YAML_TAG_TOKEN: + handle = PyUnicode_FromString(token.data.tag.handle) + suffix = PyUnicode_FromString(token.data.tag.suffix) + if not handle: + handle = None + return TagToken((handle, suffix), start_mark, end_mark) + elif token.type == YAML_SCALAR_TOKEN: + value = PyUnicode_DecodeUTF8(token.data.scalar.value, + token.data.scalar.length, 'strict') + plain = False + style = None + if token.data.scalar.style == YAML_PLAIN_SCALAR_STYLE: + plain = True + style = u'' + elif token.data.scalar.style == YAML_SINGLE_QUOTED_SCALAR_STYLE: + style = u'\'' + elif token.data.scalar.style == YAML_DOUBLE_QUOTED_SCALAR_STYLE: + style = u'"' + elif token.data.scalar.style == YAML_LITERAL_SCALAR_STYLE: + style = u'|' + elif token.data.scalar.style == YAML_FOLDED_SCALAR_STYLE: + style = u'>' + return ScalarToken(value, plain, + start_mark, end_mark, style) + else: + if PY_MAJOR_VERSION < 3: + raise ValueError("unknown token type") + else: + raise ValueError(u"unknown token type") + + def get_token(self): + if self.current_token is not None: + value = self.current_token + self.current_token = None + else: + value = self._scan() + return value + + def peek_token(self): + if self.current_token is None: + self.current_token = self._scan() + return self.current_token + + def check_token(self, *choices): + if self.current_token is None: + self.current_token = self._scan() + if self.current_token is None: + return False + if not choices: + return True + token_class = self.current_token.__class__ + for choice in choices: + if token_class is choice: + return True + return False + + def raw_parse(self): + cdef yaml_event_t event + cdef int done + cdef int count + count = 0 + done = 0 + while done == 0: + if yaml_parser_parse(&self.parser, &event) == 0: + error = self._parser_error() + raise error + if event.type == YAML_NO_EVENT: + done = 1 + else: + count = count+1 + yaml_event_delete(&event) + return count + + cdef object _parse(self): + cdef yaml_event_t event + if yaml_parser_parse(&self.parser, &event) == 0: + error = self._parser_error() + raise error + event_object = self._event_to_object(&event) + yaml_event_delete(&event) + return event_object + + cdef object _event_to_object(self, yaml_event_t *event): + cdef yaml_tag_directive_t *tag_directive + start_mark = Mark(self.stream_name, + event.start_mark.index, + event.start_mark.line, + event.start_mark.column, + None, None) + end_mark = Mark(self.stream_name, + event.end_mark.index, + event.end_mark.line, + event.end_mark.column, + None, None) + if event.type == YAML_NO_EVENT: + return None + elif event.type == YAML_STREAM_START_EVENT: + encoding = None + if event.data.stream_start.encoding == YAML_UTF8_ENCODING: + if self.unicode_source == 0: + encoding = u"utf-8" + elif event.data.stream_start.encoding == YAML_UTF16LE_ENCODING: + encoding = u"utf-16-le" + elif event.data.stream_start.encoding == YAML_UTF16BE_ENCODING: + encoding = u"utf-16-be" + return StreamStartEvent(start_mark, end_mark, encoding) + elif event.type == YAML_STREAM_END_EVENT: + return StreamEndEvent(start_mark, end_mark) + elif event.type == YAML_DOCUMENT_START_EVENT: + explicit = False + if event.data.document_start.implicit == 0: + explicit = True + version = None + if event.data.document_start.version_directive != NULL: + version = (event.data.document_start.version_directive.major, + event.data.document_start.version_directive.minor) + tags = None + if event.data.document_start.tag_directives.start != NULL: + tags = {} + tag_directive = event.data.document_start.tag_directives.start + while tag_directive != event.data.document_start.tag_directives.end: + handle = PyUnicode_FromString(tag_directive.handle) + prefix = PyUnicode_FromString(tag_directive.prefix) + tags[handle] = prefix + tag_directive = tag_directive+1 + return DocumentStartEvent(start_mark, end_mark, + explicit, version, tags) + elif event.type == YAML_DOCUMENT_END_EVENT: + explicit = False + if event.data.document_end.implicit == 0: + explicit = True + return DocumentEndEvent(start_mark, end_mark, explicit) + elif event.type == YAML_ALIAS_EVENT: + anchor = PyUnicode_FromString(event.data.alias.anchor) + return AliasEvent(anchor, start_mark, end_mark) + elif event.type == YAML_SCALAR_EVENT: + anchor = None + if event.data.scalar.anchor != NULL: + anchor = PyUnicode_FromString(event.data.scalar.anchor) + tag = None + if event.data.scalar.tag != NULL: + tag = PyUnicode_FromString(event.data.scalar.tag) + value = PyUnicode_DecodeUTF8(event.data.scalar.value, + event.data.scalar.length, 'strict') + plain_implicit = False + if event.data.scalar.plain_implicit == 1: + plain_implicit = True + quoted_implicit = False + if event.data.scalar.quoted_implicit == 1: + quoted_implicit = True + style = None + if event.data.scalar.style == YAML_PLAIN_SCALAR_STYLE: + style = u'' + elif event.data.scalar.style == YAML_SINGLE_QUOTED_SCALAR_STYLE: + style = u'\'' + elif event.data.scalar.style == YAML_DOUBLE_QUOTED_SCALAR_STYLE: + style = u'"' + elif event.data.scalar.style == YAML_LITERAL_SCALAR_STYLE: + style = u'|' + elif event.data.scalar.style == YAML_FOLDED_SCALAR_STYLE: + style = u'>' + return ScalarEvent(anchor, tag, + (plain_implicit, quoted_implicit), + value, start_mark, end_mark, style) + elif event.type == YAML_SEQUENCE_START_EVENT: + anchor = None + if event.data.sequence_start.anchor != NULL: + anchor = PyUnicode_FromString(event.data.sequence_start.anchor) + tag = None + if event.data.sequence_start.tag != NULL: + tag = PyUnicode_FromString(event.data.sequence_start.tag) + implicit = False + if event.data.sequence_start.implicit == 1: + implicit = True + flow_style = None + if event.data.sequence_start.style == YAML_FLOW_SEQUENCE_STYLE: + flow_style = True + elif event.data.sequence_start.style == YAML_BLOCK_SEQUENCE_STYLE: + flow_style = False + return SequenceStartEvent(anchor, tag, implicit, + start_mark, end_mark, flow_style) + elif event.type == YAML_MAPPING_START_EVENT: + anchor = None + if event.data.mapping_start.anchor != NULL: + anchor = PyUnicode_FromString(event.data.mapping_start.anchor) + tag = None + if event.data.mapping_start.tag != NULL: + tag = PyUnicode_FromString(event.data.mapping_start.tag) + implicit = False + if event.data.mapping_start.implicit == 1: + implicit = True + flow_style = None + if event.data.mapping_start.style == YAML_FLOW_MAPPING_STYLE: + flow_style = True + elif event.data.mapping_start.style == YAML_BLOCK_MAPPING_STYLE: + flow_style = False + return MappingStartEvent(anchor, tag, implicit, + start_mark, end_mark, flow_style) + elif event.type == YAML_SEQUENCE_END_EVENT: + return SequenceEndEvent(start_mark, end_mark) + elif event.type == YAML_MAPPING_END_EVENT: + return MappingEndEvent(start_mark, end_mark) + else: + if PY_MAJOR_VERSION < 3: + raise ValueError("unknown event type") + else: + raise ValueError(u"unknown event type") + + def get_event(self): + if self.current_event is not None: + value = self.current_event + self.current_event = None + else: + value = self._parse() + return value + + def peek_event(self): + if self.current_event is None: + self.current_event = self._parse() + return self.current_event + + def check_event(self, *choices): + if self.current_event is None: + self.current_event = self._parse() + if self.current_event is None: + return False + if not choices: + return True + event_class = self.current_event.__class__ + for choice in choices: + if event_class is choice: + return True + return False + + def check_node(self): + self._parse_next_event() + if self.parsed_event.type == YAML_STREAM_START_EVENT: + yaml_event_delete(&self.parsed_event) + self._parse_next_event() + if self.parsed_event.type != YAML_STREAM_END_EVENT: + return True + return False + + def get_node(self): + self._parse_next_event() + if self.parsed_event.type != YAML_STREAM_END_EVENT: + return self._compose_document() + + def get_single_node(self): + self._parse_next_event() + yaml_event_delete(&self.parsed_event) + self._parse_next_event() + document = None + if self.parsed_event.type != YAML_STREAM_END_EVENT: + document = self._compose_document() + self._parse_next_event() + if self.parsed_event.type != YAML_STREAM_END_EVENT: + mark = Mark(self.stream_name, + self.parsed_event.start_mark.index, + self.parsed_event.start_mark.line, + self.parsed_event.start_mark.column, + None, None) + if PY_MAJOR_VERSION < 3: + raise ComposerError("expected a single document in the stream", + document.start_mark, "but found another document", mark) + else: + raise ComposerError(u"expected a single document in the stream", + document.start_mark, u"but found another document", mark) + return document + + cdef object _compose_document(self): + yaml_event_delete(&self.parsed_event) + node = self._compose_node(None, None) + self._parse_next_event() + yaml_event_delete(&self.parsed_event) + self.anchors = {} + return node + + cdef object _compose_node(self, object parent, object index): + self._parse_next_event() + if self.parsed_event.type == YAML_ALIAS_EVENT: + anchor = PyUnicode_FromString(self.parsed_event.data.alias.anchor) + if anchor not in self.anchors: + mark = Mark(self.stream_name, + self.parsed_event.start_mark.index, + self.parsed_event.start_mark.line, + self.parsed_event.start_mark.column, + None, None) + if PY_MAJOR_VERSION < 3: + raise ComposerError(None, None, "found undefined alias", mark) + else: + raise ComposerError(None, None, u"found undefined alias", mark) + yaml_event_delete(&self.parsed_event) + return self.anchors[anchor] + anchor = None + if self.parsed_event.type == YAML_SCALAR_EVENT \ + and self.parsed_event.data.scalar.anchor != NULL: + anchor = PyUnicode_FromString(self.parsed_event.data.scalar.anchor) + elif self.parsed_event.type == YAML_SEQUENCE_START_EVENT \ + and self.parsed_event.data.sequence_start.anchor != NULL: + anchor = PyUnicode_FromString(self.parsed_event.data.sequence_start.anchor) + elif self.parsed_event.type == YAML_MAPPING_START_EVENT \ + and self.parsed_event.data.mapping_start.anchor != NULL: + anchor = PyUnicode_FromString(self.parsed_event.data.mapping_start.anchor) + if anchor is not None: + if anchor in self.anchors: + mark = Mark(self.stream_name, + self.parsed_event.start_mark.index, + self.parsed_event.start_mark.line, + self.parsed_event.start_mark.column, + None, None) + if PY_MAJOR_VERSION < 3: + raise ComposerError("found duplicate anchor; first occurrence", + self.anchors[anchor].start_mark, "second occurrence", mark) + else: + raise ComposerError(u"found duplicate anchor; first occurrence", + self.anchors[anchor].start_mark, u"second occurrence", mark) + self.descend_resolver(parent, index) + if self.parsed_event.type == YAML_SCALAR_EVENT: + node = self._compose_scalar_node(anchor) + elif self.parsed_event.type == YAML_SEQUENCE_START_EVENT: + node = self._compose_sequence_node(anchor) + elif self.parsed_event.type == YAML_MAPPING_START_EVENT: + node = self._compose_mapping_node(anchor) + self.ascend_resolver() + return node + + cdef _compose_scalar_node(self, object anchor): + start_mark = Mark(self.stream_name, + self.parsed_event.start_mark.index, + self.parsed_event.start_mark.line, + self.parsed_event.start_mark.column, + None, None) + end_mark = Mark(self.stream_name, + self.parsed_event.end_mark.index, + self.parsed_event.end_mark.line, + self.parsed_event.end_mark.column, + None, None) + value = PyUnicode_DecodeUTF8(self.parsed_event.data.scalar.value, + self.parsed_event.data.scalar.length, 'strict') + plain_implicit = False + if self.parsed_event.data.scalar.plain_implicit == 1: + plain_implicit = True + quoted_implicit = False + if self.parsed_event.data.scalar.quoted_implicit == 1: + quoted_implicit = True + if self.parsed_event.data.scalar.tag == NULL \ + or (self.parsed_event.data.scalar.tag[0] == c'!' + and self.parsed_event.data.scalar.tag[1] == c'\0'): + tag = self.resolve(ScalarNode, value, (plain_implicit, quoted_implicit)) + else: + tag = PyUnicode_FromString(self.parsed_event.data.scalar.tag) + style = None + if self.parsed_event.data.scalar.style == YAML_PLAIN_SCALAR_STYLE: + style = u'' + elif self.parsed_event.data.scalar.style == YAML_SINGLE_QUOTED_SCALAR_STYLE: + style = u'\'' + elif self.parsed_event.data.scalar.style == YAML_DOUBLE_QUOTED_SCALAR_STYLE: + style = u'"' + elif self.parsed_event.data.scalar.style == YAML_LITERAL_SCALAR_STYLE: + style = u'|' + elif self.parsed_event.data.scalar.style == YAML_FOLDED_SCALAR_STYLE: + style = u'>' + node = ScalarNode(tag, value, start_mark, end_mark, style) + if anchor is not None: + self.anchors[anchor] = node + yaml_event_delete(&self.parsed_event) + return node + + cdef _compose_sequence_node(self, object anchor): + cdef int index + start_mark = Mark(self.stream_name, + self.parsed_event.start_mark.index, + self.parsed_event.start_mark.line, + self.parsed_event.start_mark.column, + None, None) + implicit = False + if self.parsed_event.data.sequence_start.implicit == 1: + implicit = True + if self.parsed_event.data.sequence_start.tag == NULL \ + or (self.parsed_event.data.sequence_start.tag[0] == c'!' + and self.parsed_event.data.sequence_start.tag[1] == c'\0'): + tag = self.resolve(SequenceNode, None, implicit) + else: + tag = PyUnicode_FromString(self.parsed_event.data.sequence_start.tag) + flow_style = None + if self.parsed_event.data.sequence_start.style == YAML_FLOW_SEQUENCE_STYLE: + flow_style = True + elif self.parsed_event.data.sequence_start.style == YAML_BLOCK_SEQUENCE_STYLE: + flow_style = False + value = [] + node = SequenceNode(tag, value, start_mark, None, flow_style) + if anchor is not None: + self.anchors[anchor] = node + yaml_event_delete(&self.parsed_event) + index = 0 + self._parse_next_event() + while self.parsed_event.type != YAML_SEQUENCE_END_EVENT: + value.append(self._compose_node(node, index)) + index = index+1 + self._parse_next_event() + node.end_mark = Mark(self.stream_name, + self.parsed_event.end_mark.index, + self.parsed_event.end_mark.line, + self.parsed_event.end_mark.column, + None, None) + yaml_event_delete(&self.parsed_event) + return node + + cdef _compose_mapping_node(self, object anchor): + start_mark = Mark(self.stream_name, + self.parsed_event.start_mark.index, + self.parsed_event.start_mark.line, + self.parsed_event.start_mark.column, + None, None) + implicit = False + if self.parsed_event.data.mapping_start.implicit == 1: + implicit = True + if self.parsed_event.data.mapping_start.tag == NULL \ + or (self.parsed_event.data.mapping_start.tag[0] == c'!' + and self.parsed_event.data.mapping_start.tag[1] == c'\0'): + tag = self.resolve(MappingNode, None, implicit) + else: + tag = PyUnicode_FromString(self.parsed_event.data.mapping_start.tag) + flow_style = None + if self.parsed_event.data.mapping_start.style == YAML_FLOW_MAPPING_STYLE: + flow_style = True + elif self.parsed_event.data.mapping_start.style == YAML_BLOCK_MAPPING_STYLE: + flow_style = False + value = [] + node = MappingNode(tag, value, start_mark, None, flow_style) + if anchor is not None: + self.anchors[anchor] = node + yaml_event_delete(&self.parsed_event) + self._parse_next_event() + while self.parsed_event.type != YAML_MAPPING_END_EVENT: + item_key = self._compose_node(node, None) + item_value = self._compose_node(node, item_key) + value.append((item_key, item_value)) + self._parse_next_event() + node.end_mark = Mark(self.stream_name, + self.parsed_event.end_mark.index, + self.parsed_event.end_mark.line, + self.parsed_event.end_mark.column, + None, None) + yaml_event_delete(&self.parsed_event) + return node + + cdef int _parse_next_event(self) except 0: + if self.parsed_event.type == YAML_NO_EVENT: + if yaml_parser_parse(&self.parser, &self.parsed_event) == 0: + error = self._parser_error() + raise error + return 1 + +cdef int input_handler(void *data, char *buffer, size_t size, size_t *read) except 0: + cdef CParser parser + parser = data + if parser.stream_cache is None: + value = parser.stream.read(size) + if PyUnicode_CheckExact(value) != 0: + value = PyUnicode_AsUTF8String(value) + parser.unicode_source = 1 + if PyString_CheckExact(value) == 0: + if PY_MAJOR_VERSION < 3: + raise TypeError("a string value is expected") + else: + raise TypeError(u"a string value is expected") + parser.stream_cache = value + parser.stream_cache_pos = 0 + parser.stream_cache_len = PyString_GET_SIZE(value) + if (parser.stream_cache_len - parser.stream_cache_pos) < size: + size = parser.stream_cache_len - parser.stream_cache_pos + if size > 0: + memcpy(buffer, PyString_AS_STRING(parser.stream_cache) + + parser.stream_cache_pos, size) + read[0] = size + parser.stream_cache_pos += size + if parser.stream_cache_pos == parser.stream_cache_len: + parser.stream_cache = None + return 1 + +cdef class CEmitter: + + cdef yaml_emitter_t emitter + + cdef object stream + + cdef int document_start_implicit + cdef int document_end_implicit + cdef object use_version + cdef object use_tags + + cdef object serialized_nodes + cdef object anchors + cdef int last_alias_id + cdef int closed + cdef int dump_unicode + cdef object use_encoding + + def __init__(self, stream, canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, encoding=None, + explicit_start=None, explicit_end=None, version=None, tags=None): + if yaml_emitter_initialize(&self.emitter) == 0: + raise MemoryError + self.stream = stream + self.dump_unicode = 0 + if PY_MAJOR_VERSION < 3: + if getattr3(stream, 'encoding', None): + self.dump_unicode = 1 + else: + if hasattr(stream, u'encoding'): + self.dump_unicode = 1 + self.use_encoding = encoding + yaml_emitter_set_output(&self.emitter, output_handler, self) + if canonical: + yaml_emitter_set_canonical(&self.emitter, 1) + if indent is not None: + yaml_emitter_set_indent(&self.emitter, indent) + if width is not None: + yaml_emitter_set_width(&self.emitter, width) + if allow_unicode: + yaml_emitter_set_unicode(&self.emitter, 1) + if line_break is not None: + if line_break == '\r': + yaml_emitter_set_break(&self.emitter, YAML_CR_BREAK) + elif line_break == '\n': + yaml_emitter_set_break(&self.emitter, YAML_LN_BREAK) + elif line_break == '\r\n': + yaml_emitter_set_break(&self.emitter, YAML_CRLN_BREAK) + self.document_start_implicit = 1 + if explicit_start: + self.document_start_implicit = 0 + self.document_end_implicit = 1 + if explicit_end: + self.document_end_implicit = 0 + self.use_version = version + self.use_tags = tags + self.serialized_nodes = {} + self.anchors = {} + self.last_alias_id = 0 + self.closed = -1 + + def __dealloc__(self): + yaml_emitter_delete(&self.emitter) + + def dispose(self): + pass + + cdef object _emitter_error(self): + if self.emitter.error == YAML_MEMORY_ERROR: + return MemoryError + elif self.emitter.error == YAML_EMITTER_ERROR: + if PY_MAJOR_VERSION < 3: + problem = self.emitter.problem + else: + problem = PyUnicode_FromString(self.emitter.problem) + return EmitterError(problem) + if PY_MAJOR_VERSION < 3: + raise ValueError("no emitter error") + else: + raise ValueError(u"no emitter error") + + cdef int _object_to_event(self, object event_object, yaml_event_t *event) except 0: + cdef yaml_encoding_t encoding + cdef yaml_version_directive_t version_directive_value + cdef yaml_version_directive_t *version_directive + cdef yaml_tag_directive_t tag_directives_value[128] + cdef yaml_tag_directive_t *tag_directives_start + cdef yaml_tag_directive_t *tag_directives_end + cdef int implicit + cdef int plain_implicit + cdef int quoted_implicit + cdef char *anchor + cdef char *tag + cdef char *value + cdef int length + cdef yaml_scalar_style_t scalar_style + cdef yaml_sequence_style_t sequence_style + cdef yaml_mapping_style_t mapping_style + event_class = event_object.__class__ + if event_class is StreamStartEvent: + encoding = YAML_UTF8_ENCODING + if event_object.encoding == u'utf-16-le' or event_object.encoding == 'utf-16-le': + encoding = YAML_UTF16LE_ENCODING + elif event_object.encoding == u'utf-16-be' or event_object.encoding == 'utf-16-be': + encoding = YAML_UTF16BE_ENCODING + if event_object.encoding is None: + self.dump_unicode = 1 + if self.dump_unicode == 1: + encoding = YAML_UTF8_ENCODING + yaml_stream_start_event_initialize(event, encoding) + elif event_class is StreamEndEvent: + yaml_stream_end_event_initialize(event) + elif event_class is DocumentStartEvent: + version_directive = NULL + if event_object.version: + version_directive_value.major = event_object.version[0] + version_directive_value.minor = event_object.version[1] + version_directive = &version_directive_value + tag_directives_start = NULL + tag_directives_end = NULL + if event_object.tags: + if len(event_object.tags) > 128: + if PY_MAJOR_VERSION < 3: + raise ValueError("too many tags") + else: + raise ValueError(u"too many tags") + tag_directives_start = tag_directives_value + tag_directives_end = tag_directives_value + cache = [] + for handle in event_object.tags: + prefix = event_object.tags[handle] + if PyUnicode_CheckExact(handle): + handle = PyUnicode_AsUTF8String(handle) + cache.append(handle) + if not PyString_CheckExact(handle): + if PY_MAJOR_VERSION < 3: + raise TypeError("tag handle must be a string") + else: + raise TypeError(u"tag handle must be a string") + tag_directives_end.handle = PyString_AS_STRING(handle) + if PyUnicode_CheckExact(prefix): + prefix = PyUnicode_AsUTF8String(prefix) + cache.append(prefix) + if not PyString_CheckExact(prefix): + if PY_MAJOR_VERSION < 3: + raise TypeError("tag prefix must be a string") + else: + raise TypeError(u"tag prefix must be a string") + tag_directives_end.prefix = PyString_AS_STRING(prefix) + tag_directives_end = tag_directives_end+1 + implicit = 1 + if event_object.explicit: + implicit = 0 + if yaml_document_start_event_initialize(event, version_directive, + tag_directives_start, tag_directives_end, implicit) == 0: + raise MemoryError + elif event_class is DocumentEndEvent: + implicit = 1 + if event_object.explicit: + implicit = 0 + yaml_document_end_event_initialize(event, implicit) + elif event_class is AliasEvent: + anchor = NULL + anchor_object = event_object.anchor + if PyUnicode_CheckExact(anchor_object): + anchor_object = PyUnicode_AsUTF8String(anchor_object) + if not PyString_CheckExact(anchor_object): + if PY_MAJOR_VERSION < 3: + raise TypeError("anchor must be a string") + else: + raise TypeError(u"anchor must be a string") + anchor = PyString_AS_STRING(anchor_object) + if yaml_alias_event_initialize(event, anchor) == 0: + raise MemoryError + elif event_class is ScalarEvent: + anchor = NULL + anchor_object = event_object.anchor + if anchor_object is not None: + if PyUnicode_CheckExact(anchor_object): + anchor_object = PyUnicode_AsUTF8String(anchor_object) + if not PyString_CheckExact(anchor_object): + if PY_MAJOR_VERSION < 3: + raise TypeError("anchor must be a string") + else: + raise TypeError(u"anchor must be a string") + anchor = PyString_AS_STRING(anchor_object) + tag = NULL + tag_object = event_object.tag + if tag_object is not None: + if PyUnicode_CheckExact(tag_object): + tag_object = PyUnicode_AsUTF8String(tag_object) + if not PyString_CheckExact(tag_object): + if PY_MAJOR_VERSION < 3: + raise TypeError("tag must be a string") + else: + raise TypeError(u"tag must be a string") + tag = PyString_AS_STRING(tag_object) + value_object = event_object.value + if PyUnicode_CheckExact(value_object): + value_object = PyUnicode_AsUTF8String(value_object) + if not PyString_CheckExact(value_object): + if PY_MAJOR_VERSION < 3: + raise TypeError("value must be a string") + else: + raise TypeError(u"value must be a string") + value = PyString_AS_STRING(value_object) + length = PyString_GET_SIZE(value_object) + plain_implicit = 0 + quoted_implicit = 0 + if event_object.implicit is not None: + plain_implicit = event_object.implicit[0] + quoted_implicit = event_object.implicit[1] + style_object = event_object.style + scalar_style = YAML_PLAIN_SCALAR_STYLE + if style_object == "'" or style_object == u"'": + scalar_style = YAML_SINGLE_QUOTED_SCALAR_STYLE + elif style_object == "\"" or style_object == u"\"": + scalar_style = YAML_DOUBLE_QUOTED_SCALAR_STYLE + elif style_object == "|" or style_object == u"|": + scalar_style = YAML_LITERAL_SCALAR_STYLE + elif style_object == ">" or style_object == u">": + scalar_style = YAML_FOLDED_SCALAR_STYLE + if yaml_scalar_event_initialize(event, anchor, tag, value, length, + plain_implicit, quoted_implicit, scalar_style) == 0: + raise MemoryError + elif event_class is SequenceStartEvent: + anchor = NULL + anchor_object = event_object.anchor + if anchor_object is not None: + if PyUnicode_CheckExact(anchor_object): + anchor_object = PyUnicode_AsUTF8String(anchor_object) + if not PyString_CheckExact(anchor_object): + if PY_MAJOR_VERSION < 3: + raise TypeError("anchor must be a string") + else: + raise TypeError(u"anchor must be a string") + anchor = PyString_AS_STRING(anchor_object) + tag = NULL + tag_object = event_object.tag + if tag_object is not None: + if PyUnicode_CheckExact(tag_object): + tag_object = PyUnicode_AsUTF8String(tag_object) + if not PyString_CheckExact(tag_object): + if PY_MAJOR_VERSION < 3: + raise TypeError("tag must be a string") + else: + raise TypeError(u"tag must be a string") + tag = PyString_AS_STRING(tag_object) + implicit = 0 + if event_object.implicit: + implicit = 1 + sequence_style = YAML_BLOCK_SEQUENCE_STYLE + if event_object.flow_style: + sequence_style = YAML_FLOW_SEQUENCE_STYLE + if yaml_sequence_start_event_initialize(event, anchor, tag, + implicit, sequence_style) == 0: + raise MemoryError + elif event_class is MappingStartEvent: + anchor = NULL + anchor_object = event_object.anchor + if anchor_object is not None: + if PyUnicode_CheckExact(anchor_object): + anchor_object = PyUnicode_AsUTF8String(anchor_object) + if not PyString_CheckExact(anchor_object): + if PY_MAJOR_VERSION < 3: + raise TypeError("anchor must be a string") + else: + raise TypeError(u"anchor must be a string") + anchor = PyString_AS_STRING(anchor_object) + tag = NULL + tag_object = event_object.tag + if tag_object is not None: + if PyUnicode_CheckExact(tag_object): + tag_object = PyUnicode_AsUTF8String(tag_object) + if not PyString_CheckExact(tag_object): + if PY_MAJOR_VERSION < 3: + raise TypeError("tag must be a string") + else: + raise TypeError(u"tag must be a string") + tag = PyString_AS_STRING(tag_object) + implicit = 0 + if event_object.implicit: + implicit = 1 + mapping_style = YAML_BLOCK_MAPPING_STYLE + if event_object.flow_style: + mapping_style = YAML_FLOW_MAPPING_STYLE + if yaml_mapping_start_event_initialize(event, anchor, tag, + implicit, mapping_style) == 0: + raise MemoryError + elif event_class is SequenceEndEvent: + yaml_sequence_end_event_initialize(event) + elif event_class is MappingEndEvent: + yaml_mapping_end_event_initialize(event) + else: + if PY_MAJOR_VERSION < 3: + raise TypeError("invalid event %s" % event_object) + else: + raise TypeError(u"invalid event %s" % event_object) + return 1 + + def emit(self, event_object): + cdef yaml_event_t event + self._object_to_event(event_object, &event) + if yaml_emitter_emit(&self.emitter, &event) == 0: + error = self._emitter_error() + raise error + + def open(self): + cdef yaml_event_t event + cdef yaml_encoding_t encoding + if self.closed == -1: + if self.use_encoding == u'utf-16-le' or self.use_encoding == 'utf-16-le': + encoding = YAML_UTF16LE_ENCODING + elif self.use_encoding == u'utf-16-be' or self.use_encoding == 'utf-16-be': + encoding = YAML_UTF16BE_ENCODING + else: + encoding = YAML_UTF8_ENCODING + if self.use_encoding is None: + self.dump_unicode = 1 + if self.dump_unicode == 1: + encoding = YAML_UTF8_ENCODING + yaml_stream_start_event_initialize(&event, encoding) + if yaml_emitter_emit(&self.emitter, &event) == 0: + error = self._emitter_error() + raise error + self.closed = 0 + elif self.closed == 1: + if PY_MAJOR_VERSION < 3: + raise SerializerError("serializer is closed") + else: + raise SerializerError(u"serializer is closed") + else: + if PY_MAJOR_VERSION < 3: + raise SerializerError("serializer is already opened") + else: + raise SerializerError(u"serializer is already opened") + + def close(self): + cdef yaml_event_t event + if self.closed == -1: + if PY_MAJOR_VERSION < 3: + raise SerializerError("serializer is not opened") + else: + raise SerializerError(u"serializer is not opened") + elif self.closed == 0: + yaml_stream_end_event_initialize(&event) + if yaml_emitter_emit(&self.emitter, &event) == 0: + error = self._emitter_error() + raise error + self.closed = 1 + + def serialize(self, node): + cdef yaml_event_t event + cdef yaml_version_directive_t version_directive_value + cdef yaml_version_directive_t *version_directive + cdef yaml_tag_directive_t tag_directives_value[128] + cdef yaml_tag_directive_t *tag_directives_start + cdef yaml_tag_directive_t *tag_directives_end + if self.closed == -1: + if PY_MAJOR_VERSION < 3: + raise SerializerError("serializer is not opened") + else: + raise SerializerError(u"serializer is not opened") + elif self.closed == 1: + if PY_MAJOR_VERSION < 3: + raise SerializerError("serializer is closed") + else: + raise SerializerError(u"serializer is closed") + cache = [] + version_directive = NULL + if self.use_version: + version_directive_value.major = self.use_version[0] + version_directive_value.minor = self.use_version[1] + version_directive = &version_directive_value + tag_directives_start = NULL + tag_directives_end = NULL + if self.use_tags: + if len(self.use_tags) > 128: + if PY_MAJOR_VERSION < 3: + raise ValueError("too many tags") + else: + raise ValueError(u"too many tags") + tag_directives_start = tag_directives_value + tag_directives_end = tag_directives_value + for handle in self.use_tags: + prefix = self.use_tags[handle] + if PyUnicode_CheckExact(handle): + handle = PyUnicode_AsUTF8String(handle) + cache.append(handle) + if not PyString_CheckExact(handle): + if PY_MAJOR_VERSION < 3: + raise TypeError("tag handle must be a string") + else: + raise TypeError(u"tag handle must be a string") + tag_directives_end.handle = PyString_AS_STRING(handle) + if PyUnicode_CheckExact(prefix): + prefix = PyUnicode_AsUTF8String(prefix) + cache.append(prefix) + if not PyString_CheckExact(prefix): + if PY_MAJOR_VERSION < 3: + raise TypeError("tag prefix must be a string") + else: + raise TypeError(u"tag prefix must be a string") + tag_directives_end.prefix = PyString_AS_STRING(prefix) + tag_directives_end = tag_directives_end+1 + if yaml_document_start_event_initialize(&event, version_directive, + tag_directives_start, tag_directives_end, + self.document_start_implicit) == 0: + raise MemoryError + if yaml_emitter_emit(&self.emitter, &event) == 0: + error = self._emitter_error() + raise error + self._anchor_node(node) + self._serialize_node(node, None, None) + yaml_document_end_event_initialize(&event, self.document_end_implicit) + if yaml_emitter_emit(&self.emitter, &event) == 0: + error = self._emitter_error() + raise error + self.serialized_nodes = {} + self.anchors = {} + self.last_alias_id = 0 + + cdef int _anchor_node(self, object node) except 0: + if node in self.anchors: + if self.anchors[node] is None: + self.last_alias_id = self.last_alias_id+1 + self.anchors[node] = u"id%03d" % self.last_alias_id + else: + self.anchors[node] = None + node_class = node.__class__ + if node_class is SequenceNode: + for item in node.value: + self._anchor_node(item) + elif node_class is MappingNode: + for key, value in node.value: + self._anchor_node(key) + self._anchor_node(value) + return 1 + + cdef int _serialize_node(self, object node, object parent, object index) except 0: + cdef yaml_event_t event + cdef int implicit + cdef int plain_implicit + cdef int quoted_implicit + cdef char *anchor + cdef char *tag + cdef char *value + cdef int length + cdef int item_index + cdef yaml_scalar_style_t scalar_style + cdef yaml_sequence_style_t sequence_style + cdef yaml_mapping_style_t mapping_style + anchor_object = self.anchors[node] + anchor = NULL + if anchor_object is not None: + if PyUnicode_CheckExact(anchor_object): + anchor_object = PyUnicode_AsUTF8String(anchor_object) + if not PyString_CheckExact(anchor_object): + if PY_MAJOR_VERSION < 3: + raise TypeError("anchor must be a string") + else: + raise TypeError(u"anchor must be a string") + anchor = PyString_AS_STRING(anchor_object) + if node in self.serialized_nodes: + if yaml_alias_event_initialize(&event, anchor) == 0: + raise MemoryError + if yaml_emitter_emit(&self.emitter, &event) == 0: + error = self._emitter_error() + raise error + else: + node_class = node.__class__ + self.serialized_nodes[node] = True + self.descend_resolver(parent, index) + if node_class is ScalarNode: + plain_implicit = 0 + quoted_implicit = 0 + tag_object = node.tag + if self.resolve(ScalarNode, node.value, (True, False)) == tag_object: + plain_implicit = 1 + if self.resolve(ScalarNode, node.value, (False, True)) == tag_object: + quoted_implicit = 1 + tag = NULL + if tag_object is not None: + if PyUnicode_CheckExact(tag_object): + tag_object = PyUnicode_AsUTF8String(tag_object) + if not PyString_CheckExact(tag_object): + if PY_MAJOR_VERSION < 3: + raise TypeError("tag must be a string") + else: + raise TypeError(u"tag must be a string") + tag = PyString_AS_STRING(tag_object) + value_object = node.value + if PyUnicode_CheckExact(value_object): + value_object = PyUnicode_AsUTF8String(value_object) + if not PyString_CheckExact(value_object): + if PY_MAJOR_VERSION < 3: + raise TypeError("value must be a string") + else: + raise TypeError(u"value must be a string") + value = PyString_AS_STRING(value_object) + length = PyString_GET_SIZE(value_object) + style_object = node.style + scalar_style = YAML_PLAIN_SCALAR_STYLE + if style_object == "'" or style_object == u"'": + scalar_style = YAML_SINGLE_QUOTED_SCALAR_STYLE + elif style_object == "\"" or style_object == u"\"": + scalar_style = YAML_DOUBLE_QUOTED_SCALAR_STYLE + elif style_object == "|" or style_object == u"|": + scalar_style = YAML_LITERAL_SCALAR_STYLE + elif style_object == ">" or style_object == u">": + scalar_style = YAML_FOLDED_SCALAR_STYLE + if yaml_scalar_event_initialize(&event, anchor, tag, value, length, + plain_implicit, quoted_implicit, scalar_style) == 0: + raise MemoryError + if yaml_emitter_emit(&self.emitter, &event) == 0: + error = self._emitter_error() + raise error + elif node_class is SequenceNode: + implicit = 0 + tag_object = node.tag + if self.resolve(SequenceNode, node.value, True) == tag_object: + implicit = 1 + tag = NULL + if tag_object is not None: + if PyUnicode_CheckExact(tag_object): + tag_object = PyUnicode_AsUTF8String(tag_object) + if not PyString_CheckExact(tag_object): + if PY_MAJOR_VERSION < 3: + raise TypeError("tag must be a string") + else: + raise TypeError(u"tag must be a string") + tag = PyString_AS_STRING(tag_object) + sequence_style = YAML_BLOCK_SEQUENCE_STYLE + if node.flow_style: + sequence_style = YAML_FLOW_SEQUENCE_STYLE + if yaml_sequence_start_event_initialize(&event, anchor, tag, + implicit, sequence_style) == 0: + raise MemoryError + if yaml_emitter_emit(&self.emitter, &event) == 0: + error = self._emitter_error() + raise error + item_index = 0 + for item in node.value: + self._serialize_node(item, node, item_index) + item_index = item_index+1 + yaml_sequence_end_event_initialize(&event) + if yaml_emitter_emit(&self.emitter, &event) == 0: + error = self._emitter_error() + raise error + elif node_class is MappingNode: + implicit = 0 + tag_object = node.tag + if self.resolve(MappingNode, node.value, True) == tag_object: + implicit = 1 + tag = NULL + if tag_object is not None: + if PyUnicode_CheckExact(tag_object): + tag_object = PyUnicode_AsUTF8String(tag_object) + if not PyString_CheckExact(tag_object): + if PY_MAJOR_VERSION < 3: + raise TypeError("tag must be a string") + else: + raise TypeError(u"tag must be a string") + tag = PyString_AS_STRING(tag_object) + mapping_style = YAML_BLOCK_MAPPING_STYLE + if node.flow_style: + mapping_style = YAML_FLOW_MAPPING_STYLE + if yaml_mapping_start_event_initialize(&event, anchor, tag, + implicit, mapping_style) == 0: + raise MemoryError + if yaml_emitter_emit(&self.emitter, &event) == 0: + error = self._emitter_error() + raise error + for item_key, item_value in node.value: + self._serialize_node(item_key, node, None) + self._serialize_node(item_value, node, item_key) + yaml_mapping_end_event_initialize(&event) + if yaml_emitter_emit(&self.emitter, &event) == 0: + error = self._emitter_error() + raise error + self.ascend_resolver() + return 1 + +cdef int output_handler(void *data, char *buffer, size_t size) except 0: + cdef CEmitter emitter + emitter = data + if emitter.dump_unicode == 0: + value = PyString_FromStringAndSize(buffer, size) + else: + value = PyUnicode_DecodeUTF8(buffer, size, 'strict') + emitter.stream.write(value) + return 1 + -- cgit v1.2.3